Cross-model face recognition poses a major challenge due to inconsistent embeddings produced by diverse face recognition models, limiting system interoperability. Enhancing compatibility among these models is essential for scalable, maintainable face recognition systems. This paper presents the Kolmogorov-Arnold Guided Alignment (KAGA) model, optimized with Mutual Decoupled Distillation (MDD), to effectively bridge embedding discrepancies. KAGA integrates a cross-attention mechanism and a learnable Guided Alignment Embedding to unify feature spaces, while Kolmogorov-Arnold Networks ensure robustness of the transformation. MDD facilitates selective knowledge transfer without compromising class separability, and bidirectional distillation refines feature representations for improved generalization. Extensive experiments across multiple face recognition benchmarks confirm KAGA's effectiveness, demonstrating substantial gains in accuracy and cross-model compatibility compared to state-of-the-art approaches.

Palmprint recognition systems experience a significant performance decline in cross-domain scenarios due to domain shift caused by non-identity factors such as capture devices and lighting conditions. To address this issue, this paper introduces a novel deep decoupling framework, the Identity and Style Feature Decoupling Network (ISFDNet), designed to improve the model’s cross-domain generalization. ISFDNet explicitly separates stable identity-related information from variable domain-related style information within palmprint features. The framework incorporates two innovative mechanisms: at the feature level, the Spatially-Aware Separation Module (SASM) adaptively produces complementary spatial attention masks to decouple mixed features into identity and style components; at the image level, the Low-Frequency Disturbance Module (LFDM) creates stylized training samples by perturbing the low-frequency parts of images, encouraging the network to learn identity representations that are insensitive to style variations. Additionally, a carefully designed collaborative supervision strategy combines multiple losses to ensure effective decoupling. Extensive experiments on four publicly available palmprint datasets demonstrate that ISFDNet achieves top performance in both cross-domain and in-domain tests, while significantly enhancing the generalization capabilities of existing networks. The code is released at https://github.com/20201422/ISFDNet.

Current deep learning (DL)-based palmprint verification models rely on centralized training with large datasets, which raises significant privacy concerns due to the sensitive and immutable nature of biometric data. Federated learning (FL), a privacy-preserving distributed learning paradigm, offers a compelling alternative by enabling collaborative model training without the need for data sharing. However, FL-based palmprint verification faces critical challenges, including data heterogeneity from diverse identities and the absence of standardized evaluation benchmarks. This paper addresses these gaps by establishing a comprehensive benchmark for FL-based palmprint verification, which explicitly defines and evaluates two practical scenarios: closed-set and open-set verification. We propose FedPalm, a unified FL framework that balances local adaptability with global generalization. Each client trains a personalized textural expert tailored to local data and collaboratively contributes to a shared global textural expert for extracting generalized features. To further enhance verification performance, we introduce a Textural Expert Interaction Module that dynamically routes textural features among experts to generate refined side textural features. Learnable parameters are employed to model relationships between original and side features, fostering cross-texture-expert interaction and improving feature discrimination. Extensive experiments validate the effectiveness of FedPalm, demonstrating robust performance across both scenarios and providing a promising foundation for advancing FL-based palm-print verification research. The related code has been publicly available at https://github.com/Zi-YuanYang/FedPalm.

Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers’ prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition—often grounded in traditional methodologies—there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This article bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. This article systematically examines progress across key tasks, including region-of-interest (ROI) segmentation, feature extraction, and security and privacy-oriented challenges. Beyond highlighting these advancements, this article identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition.

We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown. We observe that existing models suffer from tail-versus-noise trade-off where if a model is robust against pixel noise, then its performance deteriorates on tail class samples, and vice versa. To mitigate the issue, we handle the tail class and noise samples independently. To this end, we propose TailSampler, a novel class size predictor that estimates the class cardinality of samples based on a symmetric assumption on the class-wise distribution of embedding similarities. TailSampler can be utilized to sample the tail class samples exclusively, allowing to handle them separately. Based on these facets, we build a memory-based anomaly detection model TailedCore, whose memory both well captures tail class information and is noise-robust. We extensively validate the effectiveness of TailedCore on the unsupervised long-tail noisy anomaly detection setting, and show that TailedCore outperforms the state-of-the-art in most settings. Code is available in TailedCore

Palmprint recognition has emerged as a prominent biometric authentication method due to its high discriminative power, making it suitable for IoT-based security applications. However, the traditional verification paradigm—requiring identical query and registered palmprints—poses notable limitations. This approach is inconvenient if the registered palmprint is injured. To address these challenges, we draw inspiration from biological insights into the symmetrical development of structures during embryonic growth and propose a novel Cross-Chirality Palmprint Verification (CCPV) framework. CCPV enables authentication using either palm, irrespective of which palm is registered, enhancing flexibility for IoT deployments with diverse user conditions. CCPV incorporates an innovative matching rule to improve robustness and minimize variability. This rule calculates distances by flipping the gallery and query palmprints, averaging the results to produce the final matching score. Considering all potential alignments, this approach reduces variance and boosts reliability, which is critical for ensuring seamless biometric authentication in IoT systems. Complementing this is the cross-chirality (CC) loss, which fosters a robust feature space tailored to cross-chirality matching. The CC loss ensures consistency across four palmprint variants—left, right, flipped left, and flipped right—enabling the model to extract chirality-consistent features. Extensive experiments on public datasets validate our effectiveness under closed-set and open-set scenarios. Furthermore, we demonstrate that CCPV is versatile and can seamlessly integrate with existing palmprint recognition methods to achieve superior performance. This innovation advances state-of-the-art biometric authentication and paves the way for more resilient palmprint recognition systems for IoT applications.

Palmprint recognition has received considerable attention due to its inherent discriminative characteristics. However, conventional methods largely rely on static features extracted from individual images, which limits their representational richness. To address this, we propose a dynamic palmprint verification framework that harnesses generative models to enhance feature representations through dynamic construction and matching strategies. During training, a classifier-guided generative model synthesizes class-aware pairs, and a regularization term is introduced to expand the feature space, while mitigating overfitting. For matching, we reformulate the process as a subspace projection within a locally adaptive feature space, where the original and class-conditioned generated features form the basis of the subspace. This enables the model to capture latent inter-individual relationships and achieve stronger discriminability. Extensive experiments across multiple backbones and public benchmarks validate the effectiveness and robustness of the proposed framework.

Currently global features are usually extracted directly from local patterns in palmprint verification. Furthermore, sequence features for palmprint verification are only used as local features, but the properties of sequence features are not fully utilized. To solve this issue, this paper introduces Sequence Feature Fusion Network (SF2Net) for palmprint verification. SF2Net proposes a new paradigm: using stable and spatially correlated sequence features as an intermediate bridge to generate robust global representations. SF2Net’s core mechanism is to first extract fine-grained local features that are then converted into sequence features by a sequence feature extractor (SFE). Finally, the sequence features are used as a superior input to capture high-quality global features. By fusing multi-order texture-based local features with globally extracted sequence features, SF2Net achieves superior discrimination. To ensure high accuracy even with limited training data, a hybrid loss function is proposed, which integrate a cross-entropy loss and a triplet loss. Triplet loss effectively optimizes feature separation by explicitly considering negative samples. Extensive experiments on multiple publicly available palmprint datasets demonstrate that SF2Net achieves state-of-the-art (SOTA) performance. Remarkably, even with a small training-to-testing ratio (1:9), SF2Net achieves 100% accuracy, surpassing SOTA methods under several benchmark datasets. The code is released at https://github.com/20201422/SF2Net.

Periocular and face are complementary biometrics for identity management, albeit with inherent limitations, notably in scenarios involving occlusion due to sunglasses or masks. In response to these challenges, we introduce Flexible Biometric Recognition (FBR), a novel framework designed to advance conventional face, periocular, and multimodal face-periocular biometrics across both intra- and cross-modality recognition tasks. FBR strategically utilizes the Multimodal Fusion Attention (MFA) and Multimodal Prompt Tuning (MPT) mechanisms within the Vision Transformer architecture. MFA facilitates the fusion of modalities, ensuring cohesive alignment between facial and periocular embeddings while incorporating soft-biometrics to enhance the model's ability to discriminate between individuals. The fusion of three modalities is pivotal in exploring interrelationships between different modalities. Additionally, MPT serves as a unifying bridge, intertwining inputs and promoting cross-modality interactions while preserving their distinctive characteristics. The collaborative synergy of MFA and MPT enhances the shared features of the face and periocular, with a specific emphasis on the ocular region, yielding exceptional performance in both intra-and cross-modality recognition tasks. Rigorous experimentation across four benchmark datasets validates the note-worthy performance of the FBR model. The source code is available at https://github.com/MIS-DevWorks/FBR.

Palmprint biometrics garner heightened attention in palm-scanning payment and social security due to their distinctive attributes. However, prevailing methodologies singularly prioritize texture orientation, neglecting the significant texture scale dimension. We design an innovative network for concurrently extracting intra-scale and inter-scale features to redress this limitation. This paper proposes a scale-aware competitive network (SAC-Net), which includes the Inner-Scale Competition Module (ISCM) and the Across-Scale Competition Module (ASCM) to capture texture characteristics related to orientation and scale. ISCM efficiently integrates learnable Gabor filters and a self-attention mechanism to extract rich orientation data and discern textures with long-range discriminative properties. Subsequently, ASCM leverages a competitive strategy across various scales to effectively encapsulate the competitive texture scale elements. By synergizing ISCM and ASCM, our method adeptly characterizes palm-print features. Rigorous experimentation across three benchmark datasets unequivocally demonstrates our proposed approach’s exceptional recognition performance and resilience relative to state-of-the-art alternatives.

Conditional Multimodal Biometrics (CMB) presents a promising avenue for boosting periocular biometrics performance by conditioning facial information. This paper reframes CMB as a domain adaptation problem arising from distinct distribution gaps between facial and periocular modalities. Despite shared identity labels, classifiers across these domains suffer from misalignment. To address this problem, we propose a novel approach that strategically employs adaptation techniques in embeddings and classifiers. Our novel strategy combines supervised contrastive embedding adaptation to bridge modality gaps and introduces modality transfer augmentation to enrich facial embeddings with periocular semantic cues. This augmentation procedure guides classifier adaptation towards the periocular domain. Empirical validation conducted across six diverse periocular-face datasets underscores the efficacy of the proposed method.

Touch-stroke dynamics have garnered significant attention as a means of mobile user authentication. However, current research often assumes the availability of large datasets tailored to specific smartphone applications. In response to the scarcity of real-world data and the computational limitations of smartphones, we introduce an innovative cross-domain cross-task transfer framework for mobile user authentication. Our approach harnesses auxiliary data from diverse applications and user sets to complement the data scarcity. A two-stream Transformer network is devised to enable knowledge transfer between disparate domains and tasks. This network adeptly amalgamates user-discriminative insights from various applications while refining precise embeddings tailored to a target application. Meta-learning optimization is employed to counteract negative knowledge sharing. Furthermore, we introduce a novel data augmentation technique based on feature covariance to bolster the training of robust one-class classifiers. Experimental findings showcased the efficacy of our method in harnessing heterogeneous data sources that exhibit domain and task disparities. Our approach achieved commendable performance to state-of-the-art methods with a reasonable computational burden on smartphones.

Deep learning techniques have recently been utilized for model-free age-associated gait feature extraction. However, acquiring model-free gait demands accurate pre-processing such as background subtraction, which is non-trivial in unconstrained environments. On the other hand, model-based gait can be obtained without background subtraction and is less affected by covariates. For model-based gait-based age group classification problems, present works rely solely on handcrafted features, where feature extraction is tedious and requires domain expertise. This paper proposes a deep learning approach to extract age-associated features from model-based gait for age group classification. Specifically, we first develop an unconstrained gait dataset called Multimedia University Gait Age and Gender dataset (MMU GAG). Next, the body joint coordinates are determined via pose estimation algorithms and represented as compact gait graphs via a novel part aggregation scheme. Then, a Part-AdaptIve Residual Graph Convolutional Neural Network (PairGCN) is designed for age-associated feature learning. Experiments suggest that PairGCN features are far more informative than handcrafted features, yielding up to 99% accuracy for classifying subjects as a child, adult, or senior in the MMU GAG dataset. These results suggest the feasibility of deploying Artificial Intelligence-enabled solutions for access control, surveillance, and law enforcement in unconstrained environments.

This paper presents a novel multitask learning framework for palmprint biometrics, which optimizes classification and hashing branches jointly. The classification branch within our framework facilitates the concurrent execution of three distinct tasks: identity recognition and classification of soft biometrics, encompassing gender and chirality. On the other hand, the hashing branch enables the generation of palmprint hash codes, optimizing for minimal storage as templates and efficient matching. The hashing branch derives the complementary information from these tasks by amalgamating knowledge acquired from the classification branch. This approach leads to superior overall performance compared to individual tasks in isolation. To enhance the effectiveness of multitask learning, two additional modules, an attention mechanism module and a customized gate control module, are introduced. These modules are vital in allocating higher weights to crucial channels and facilitating task-specific expert knowledge integration. Furthermore, an automatic weight adjustment module is incorporated to optimize the learning process further. This module fine-tunes the weights assigned to different tasks, improving performance. Integrating the three modules above has shown promising accuracies across various classification tasks and has notably improved authentication accuracy. The extensive experimental results validate the efficacy of our proposed framework.

Periocular and face are two common biometric modalities for identity management. Recently, the emergence of conditional biometrics has enabled the exploitation of the correlation between face and periocular to enhance each modality’s performance, in which we coin intra-modal matching in this paper. However, limitations arise in each modality, particularly when wearing sunglasses or helmets, causing the absence of periocular or facial occlusion. A biometric system empowered with inter-modal matching capability between periocular and face is essential to mitigate these challenges. This paper presents a novel reciprocal learning model that utilizes periocular and face conditioning to facilitate flexible intra-modal and inter-modal matching. To address the intra-modal matching challenge, we devise a lightweight Gated Convolutional Channel-wise Self-Attention Network that enables selective attention to shared salient periocular and face features. On the other hand, to bridge the modality gap without sacrificing the intra-modal matching performance, we propose a modality and augmentation-aware contrastive loss that incorporates semi-supervised positive sampling and alignment-specific logit rescaling. Extensive identification and verification experiments on five face-periocular datasets under the open-set protocol attest to the efficacy of our proposed methods.

In recent years, palmprints have been extensively utilized for individual verification. The abundance of sensitive information in palmprint data necessitates robust protection to ensure security and privacy without compromising system performance. Existing systems frequently use cancelable transformations to protect palmprint templates. However, if an adversary gains access to the stored database, they could initiate a replay attack before the system detects the breach and can revoke and replace the reference template. To address replay attacks while meeting template protection criteria, we propose a dual-level cancelable palmprint verification framework. In this framework, the reference template is initially transformed using a cancelable competition hashing network with a first-level token, enabling the end-to-end generation of cancelable templates. During enrollment, the system creates a negative database (NDB) using a second-level token for further protection. Due to the unique NDB-to-vector matching characteristic, a replay attack involving the matching between the reference template and a compromised instance in NDB form is infeasible. This approach effectively addresses the replay attack problem at its root. Furthermore, the dual-level protected reference template enjoys heightened security, as reversing the NDB is NP-hard. We also propose a novel NDB-to-vector matching algorithm based on matrix operations to expedite the matching process, addressing the inefficiencies of previous NDB methods reliant on dictionary-based matching rules. Extensive experiments conducted on public palmprint datasets confirm the effectiveness and generality of the proposed framework. Upon acceptance of the paper, the code will be accessible athttps://github.com/Zi-YuanYang/DCPV.

The unprecedented success of deep learning could not be achieved without the synergy of big data, computing power, and human knowledge, among which none is free. This calls for the copyright protection of deep neural networks (DNNs), which has been tackled via DNN watermarking. Due to the special structure of DNNs, backdoor watermarks have been one of the popular solutions. In this article, we first present a big picture of DNN watermarking scenarios with rigorous definitions unifying the black- and white-box concepts across watermark embedding, attack, and verification phases. Then, from the perspective of data diversity, especially adversarial and open set examples overlooked in the existing works, we rigorously reveal the vulnerability of backdoor watermarks against black-box ambiguity attacks. To solve this problem, we propose an unambiguous backdoor watermarking scheme via the design of deterministically dependent trigger samples and labels, showing that the cost of ambiguity attacks will increase from the existing linear complexity to exponential complexity. Furthermore, noting that the existing definition of backdoor fidelity is solely concerned with classification accuracy, we propose to more rigorously evaluate fidelity via examining training data feature distributions and decision boundaries before and after backdoor embedding. Incorporating the proposed prototype guided regularizer (PGR) and fine-tune all layers (FTAL) strategy, we show that backdoor fidelity can be substantially improved. Experimental results using two versions of the basic ResNet18, advanced wide residual network (WRN28_10) and EfficientNet-B0, on MNIST, CIFAR-10, CIFAR-100, and FOOD-101 classification tasks, respectively, illustrate the advantages of the proposed method.

Very low-resolution face recognition (VLRFR) poses unique challenges, such as tiny regions of interest and poor resolution due to extreme standoff distance or wide viewing angle of the acquisition devices. In this paper, we study principled approaches to elevate the recognizability of a face in the embedding space instead of the visual quality. We first formulate a robust learning-based face recognizability measure, namely recognizability index (RI), based on two criteria: (i) proximity of each face embedding against the unrecognizable faces cluster center and (ii) closeness of each face embedding against its positive and negative class prototypes. We then devise an index diversion loss to push the hard-to-recognize face embedding with low RI away from unrecognizable faces cluster to boost the RI, which reflects better recognizability. Additionally, a perceptibility attention mechanism is introduced to attend to the most recognizable face regions, which offers better explanatory and discriminative traits for embedding learning. Our proposed model is trained end-to-end and simultaneously serves recognizability-aware embedding learning and face quality estimation. To address VLRFR, our extensive evaluations on three challenging low-resolution datasets and face quality assessment demonstrate the superiority of the proposed model over the state-of-the-art methods.

A neural network trained on a classification dataset often exhibits a higher vector norm of hidden layer features for in-distribution (ID) samples, while producing relatively lower norm values on unseen instances from out-of-distribution (OOD). Despite this intriguing phenomenon being utilized in many applications, the underlying cause has not been thoroughly investigated. In this study, we demystify this very phenomenon by scrutinizing the discriminative structures concealed in the intermediate layers of a neural network. Our analysis leads to the following discoveries: (1) The feature norm is a confidence value of a classifier hidden in the network layer, specifically its maximum logit. Hence, the feature norm distinguishes OOD from ID in the same manner that a classifier confidence does. (2) The feature norm is class-agnostic, thus it can detect OOD samples across diverse discriminative models. (3) The conventional feature norm fails to capture the deactivation tendency of hidden layer neurons, which may lead to misidentification of ID samples as OOD instances. To resolve this drawback, we propose a novel negative-aware norm (NAN) that can capture both the activation and deactivation tendencies of hidden layer neurons. We conduct extensive experiments on NAN, demonstrating its efficacy and compatibility with existing OOD detectors, as well as its capability in label-free environments.

Detecting out-of-distribution (OOD) samples are crucial for machine learning models deployed in open-world environments. Classifier-based scores are a standard approach for OOD detection due to their fine-grained detection capability. However, these scores often suffer from overconfidence issues, misclassifying OOD samples distant from the in-distribution region. To address this challenge, we propose a method called Nearest Neighbor Guidance (NNGuide) that guides the classifier-based score to respect the boundary geometry of the data manifold. NNGuide reduces the overconfidence of OOD samples while preserving the fine-grained capability of the classifier-based score. We conduct extensive experiments on ImageNet OOD detection benchmarks under diverse settings, including a scenario where the ID data undergoes natural distribution shift. Our results demonstrate that NNGuide provides a significant performance improvement on the base detection scores, achieving state-of-the-art results on both AUROC, FPR95, and AUPR metrics.

In this paper, we address the black-box face reconstruction attack with two crucial requirements: query efficiency and generalizability. A practical attack must be query efficient due to limited access to the target black-box model, and the reconstructed face must be generalizable so it can be used to attack other face recognition systems. To this end, we propose a novel face reconstruction attack that optimizes the latent vector of a pre-trained StyleGAN generator. Unlike existing methods, our method is query efficient as neither training nor simultaneous updating of multiple latent vectors is required. Furthermore, we propose a simple initialization scheme that greatly enhances the generalizability of the proposed method. We demonstrate the effectiveness of our method by a thorough evaluation on LFW and CFP-FP datasets across multiple state-of-the-art face recognition models. Project Code: github.com/1ho0jin1/Black-box-Face-Reconstruction.

Smartphones have become indispensable in our lives, even for security-critical tasks. Traditional security measures such as PINs provide only one-time authentication, while biometrics enable continuous authentication in mobile devices. This paper introduces a simple, lightweight, pretrained Transformer dubbed PIEformer for open-set authentication (OSA) of multimodal touchstrokes and gait biometrics. Compared to conventional mobile closed-set authentication, OSA enables more secure and practical authentication, with genuine and impostor users disjoint from the training set. PIEFormer incorporates a novel implicit ensembling mechanism for extracting discriminative embeddings within an open-set environment and enhancing generalization performance. This approach learns multiple diverse sub-embeddings, capturing complementary aspects of biometrics data with minimal computational overhead, allowing Transformers to exhibit robust capabilities in OSA. Our proposed methods demonstrate state-of-the-art results on HMOG and BBMAS datasets, particularly in open-set scenarios compared to closed-set literature, thus bringing mobile biometric authentication closer to real-world applications.

Abstract Wearable-sensor gait signals processed using advanced machine learning algorithms are shown to be reliable for user authentication. However, no study has been reported to investigate the influence of elapsed time on wearable sensor-based gait authentication performance. This work is the first exploratory study that presents accelerometer and gyroscope signals from 144 participants with slow, normal, and fast walking speeds from 2 sessions (1-month elapse time) to evaluate IMU gait-based authentication performance. Gait signals are recorded in six positions (i.e., left and right pocket, left and right hand, handbag, and backpack). The users' identities are verified using a robust gait authentication method called Adaptive 1-Dimensional Time Invariant Learning (A1TIL). In A1TIL, 1D Local Ternary Patterns (LTP) with an adaptive threshold is proposed to extract discriminative time-invariant features from a gait cycle. In addition, a new unsupervised learning method called Kernelized Domain Adaptation (KDA) is applied to match two gait signals from different time spans for user verification. Comprehensive experiments have been conducted to assess the effectiveness of the proposed approach on a newly developed time invariant inertial sensor dataset. The promising result with an Equal Error Rate (EER) of 4.38% from slow walking speed and right pocket position across 1 month demonstrates that gait signals extracted from inertial sensors can be used as a reliable means of biometrics across time.

Correction to: Neural Computing and Applications https://doi.org/10.1007/s00521-022-07741-0 Unfortunately, the article has been published with few errors in the online publication of the article. The corrections are provided below: 1. In the original version of this article, the given and family names of Tee Connie were incorrectly structured. The name was displayed correctly in all versions at the time of publication. 2. The correct name of the fourth author should read as Andrew Beng Jin Teoh. 3. The reference number in the Introduction sections are corrected as follows: How an individual walks, combined with unique postures, has become an assertion that gait is unique [1, 2]. Many studies have shown that humans’ gait has the potential to be robust biometrics [3, 4].

Traditional biometrics identification performs matching between probe and gallery that may involve the same single or multiple biometric modalities. This paper presents a cross-matching scenario where the probe and gallery are from two distinctive biometrics, i.e., face and periocular, coined as face-periocular cross-identification (FPCI). We propose a novel contrastive loss tailored for face-periocular cross-matching to learn a joint embedding, which can be used as a gallery or a probe regardless of the biometric modality. On the other hand, a hybrid attention vision transformer is devised. The hybrid attention module performs depth-wise convolution and conv-based multi-head self-attention in parallel to aggregate global and local features of the face and periocular biometrics. Extensive experiments on three benchmark datasets demonstrate that our model sufficiently improves the performance of FPCI. Besides that, a new face-periocular dataset in the wild, the Cross-modal Face-periocular dataset, is developed for the FPCI models training.

Similarity preserving is a key ingredient of cancellable biometric scheme design. The notion ensures the accuracy performance of the biometric systems can be preserved after the cancellable biometric technique is applied. Random Projection is among the most commonly adopted method in cancellable biometric schemes. However, it is reversible subject to certain conditions, which disrupts the template irreversibility criterion. This invites vulnerabilities for random projection-based schemes. In this paper, we propose a novel transform function, namely Absolute Value Equations Transform (AVET), which non-linearly projects feature vectors to another domain. The transformed templates hold two main merits ensuring the user’s privacy, and maintaining the system’s performance simultaneously. First, by relying on the hardness of the Absolute Value Equations problem, we guarantee that AVET satisfies irreversibility. Second, by using Johnson–Lindenstrauss lemma and the inverse triangle inequality, we prove that the proposed approach has the similarity preserving property. Notably, rigorous theoretical proofs and empirical experiments are provided. The efficacy of AVET is comprehensively evaluated on both physiological and behavioral biometrics including face, ear, fingerprint, and gait. With unimodal approach, we achieve competitive performances compared to related algorithms on eight public datasets. Regarding bimodal mode, the AVET surpasses the state-of-the-art technique on all three observed datasets. To the best of our knowledge, this is the first study that attempts to develop a secure transformation to augment the role of Random Projection in the existing cancellable biometric schemes.

Low-light image enhancement, a pervasive but challenging problem, plays a central role in enhancing the visibility of an image captured in a poor illumination environment. Due to the fact that not all photons can pass the Bayer-Filter on the sensor of the color camera, in this work, we first present a De-Bayer-Filter simulator based on deep neural networks to generate a monochrome raw image from the colored raw image. Next, a fully convolutional network is proposed to achieve the low-light image enhancement by fusing colored raw data with synthesized monochrome data. Channel-wise attention is also introduced to the fusion process to establish a complementary interaction between features from colored and monochrome raw images. To train the convolutional networks, we propose a dataset with monochrome and color raw pairs named Mono-Colored Raw paired dataset (MCR) collected by using a monochrome camera without Bayer-Filter and a color camera with Bayer-Filter. The proposed pipeline takes advantages of the fusion of the virtual monochrome and the color raw images, and our extensive experiments indicate that significant improvement can be achieved by leveraging raw sensor data and data-driven learning. The project is available at https://github.com/TCL-AILab/Abandon_Bayer-Filter_See_in_the_Dark.

Multimodal biometrics has been attributed to achieving better performance compared to unimodal biometrics, despite there being some limitations on its utilization e.g. availability, deployment cost, templates management, etc. In this paper, we revolve around a generalized multimodal biometrics notion, which we coin as Conditional Multimodal Biometrics (CMB). The CMB is substantiated by a learning model which is trained with N multimodal biometrics. During enrollment and query, the trained CMB model is utilized as a feature encoder to transform any x biometric raw input(s) yielding x reference and query instances, respectively, where 1≤x≤ N. Depending on application needs, multimodal biometrics system enjoys better performance by deploying either a single biometrics, a subset, or all N modalities. As a means of realization, we consider face and periocular biometrics and propose a deep CMB network, known as CMB-Net. The CMB-Net is composed of two predictors corresponding to face and periocular with a shared-parameter convolutional backbone. Apart from classification losses for each face and periocular, a CMB loss with regularization is devised to attract periocular-face intra-subject feature embeddings and repel periocular-face inter-subject feature embeddings, whilst each face and periocular regulates one another throughout CMB-Net training. We scrutinize three CMB configurations, namely periocular conditioned by face, face conditioned by periocular and periocular-face, under the CMB regimen. Our experimental results on five periocular-face in the wild datasets demonstrate that all three CMB configurations outperform their respective baselines under both identification and verification modes.

In this paper, we focus on addressing the open-set face identification problem on a few-shot gallery by finetuning. The problem assumes a realistic scenario for face identification, where only a small number of face images is given for enrollment and any unknown identity must be rejected during identification. We observe that face recognition models pretrained on a large dataset and naively fine-tuned models perform poorly for this task. Motivated by this issue, we propose an effective fine-tuning scheme with classifier weight imprinting and exclusive BatchNorm layer tuning. For further improvement of rejection accuracy on unknown identities, we propose a novel matcher called Neighborhood Aware Cosine (NAC) that computes similarity based on neighborhood information. We validate the effectiveness of the proposed schemes thoroughly on large-scale face benchmarks across different convolutional neural network architectures. The source code for this project is available at: https://github.com/1ho0jin1/OSFI-by-FineTuning

Security enhancement via trustworthy identity authentication in Internet of Things (IoT) has soared recently. Biometrics offers a promising remedy to improve the security and utility of IoT and play a role in securing a variety of low-power and limited computing capability IoT devices to address identity management challenges. This article proposes an IoT-compliant co-learned biometric hashing network derived from palm print and palm vein dubbed PalmCohashNet. The PalmCohashNet comprises two hashing subnetworks, one for each palm modality, and is trained collaboratively to generate shared hash codes for respective modality (co-hash codes). A cross-modality hashing (CMH) loss is devised to encourage co-hash codes of palm vein and palm print from the same identity to be adjacent and consistent; meanwhile, pull the co-hash codes of each identity to a preassigned identity-specific hash centroid that is shared by both palm modalities. Two palm-based co-hash codes of a person can be generated simultaneously for deployment. The binary co-hash code is IoT compliant attributed to its highly compact form for storage and fast matching. A trained PalmCohashNet can be flexibly deployed under four operation modes: single-modality matching (print versus print or vein versus vein), multimodality matching where both print and vein are utilized, and cross-modality matching (print versus vein) depending on the IoT service context. Our empirical results on four publicly available palm databases show that the proposed method consistently outperforms state-of-the-art methods.

Low-light image enhancement plays a central role in various downstream computer vision tasks. Vision Transformers (ViTs) have recently been adapted for low-level image processing and have achieved a promising performance. However, ViTs process images in a window- or patch-based manner, compromising their computational efficiency and long-range dependency. Additionally, existing ViTs process RGB images instead of RAW data from sensors, which is sub-optimal when it comes to utilizing the rich information from RAW data. We propose a fully endto-end Conv-Transformer-based model, RawFormer, to directly utilize RAW data for low-light image enhancement. RawFormer has a structure similar to that of U-Net, but it is integrated with a thoughtfully designed Conv-Transformer Fusing (CTF) block. The CTF block combines local attention and transposed selfattention mechanisms in one module and reduces the computational overhead by adopting a transposed self-attention operation. Experiments demonstrate that RawFormer outperforms state-ofthe-art models by a significant margin on low-light RAW image enhancement tasks.

Low-resolution (LR) face recognition (LRFR) tacklestiny face imagesdetected from real-world surveillance camera footage, which are unconstrained and generally poor in quality. Owing to the absence of a million-scale labeled LR face dataset,identity-invariantdata augmentation (DA) transformations such as flipping, rotation, rescaling, etc., are applied to inflate the effective training examples with respect to the source identities for representation learning. Unfortunately, the identity-invariant property incurs additional intra-class disparity that impairs generalization performance. In this paper, we put forward a new means of DA strategy, termedidentity-extendedDA, that satisfies bothaffinityanddiversityrequirements essential to DA. We instantiate an implicit identity-extended augmentation network, or simply IDEA-Net, to realize the proposed identity-extended DA for LRFR. More specifically, training an IDEA-Net instance augments the small-scale LR (query) face dataset with identity-extended (auxiliary) face examples implicitly in the representation space. We also introduce a calibrator to regulate the disordered representation space by refining the intra-class compactness and the inter-class separation. This diminishes the distribution shift between the original and the augmented examples (affinity) and increases the learning complexity (diversity). We substantiate that IDEA-Net renders a high affinity and diversity representation space. On the other hand, our experimental results on three real-world LR face datasets demonstrate that IDEA-Nets outperform the baselines and other counterparts trained without leveraging the identity-extended examples for LRFR.

Open set recognition (OSR) models need not only discriminate between known classes but also detect unknown class samples unavailable during training. One promising approach is to learn discriminative representations over known classes with strong intra-class similarity and inter-class discrepancy. Then, the powerful class discrimination learned from the known classes can be extended to known and unknown classes. Without appropriate regularization, however, the model may learn representations trivially, collapsing unknown class representations to the known class ones. To resolve this problem, we propose Divergent Angular Representation (DivAR) based on two approaches. Firstly, DivAR maximizes its representational discrimination between known classes via a highly discriminative loss. Secondly, to ensure separation between known and unknown classes in the representation space, DivAR boosts the directional variation of representations over global samples. In addition, self-supervision is leveraged to improve the representation's robustness and extend DivAR to one-class classification. Moreover, unlike other OSR methods that require an extra machinery for inference, DivAR learns and infers in a single module. Extensive experiments on generic image datasets demonstrate the plausibility and effectiveness of DivAR for both OSR and One-Class Classification (OCC) problems.

The constant Q transform (CQT) has been shown to be one of the most effective speech signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted (subband) constant Q cepstral coefficient (CQCC) feature extraction and a back-end binary classifier, or a deep neural network (DNN) directly for further feature extraction and classification. Despite the rich literature on such a pipeline, we show in this paper that the pre-transform and hand-crafted features could simply be replaced by end-to-end DNNs. Specifically, we experimentally verify that by only using standard components, a light-weight neural network could outperform the state-of-the-art methods for the ASVspoof2019 challenge. The proposed model is termed Time-domain Synthetic Speech Detection Net (TSSDNet), having ResNet- or Inception-style structures. We further demonstrate that the proposed models also have attractive generalization capability. Trained on ASVspoof2019, they could achieve promising detection performance when tested on disjoint ASVspoof2015, significantly better than the existing cross-dataset results. This paper reveals the great potential of end-to-end DNNs for synthetic speech detection, without hand-crafted features.

Realistic low-resolution (LR) face images refer to those captured by the real-world surveillance cameras at extreme standoff distances, thereby LR and poor in quality essentially. Owing to severe scarcity of labeled data, a high-capacity deep convolution neural networks (CNN) is hardly trained to confront the realistic LR face recognition (LRFR) challenge. We introduce in this letter a dual-stream mutual information distillation network (MIND-Net), whereby the non-identity specific mutual information (MI) characterized by generic face features coexistent on realistic and synthetic LR face images are distilled to render a resolution-invariant embedding space for LRFR. For a thorough analysis, we quantify the degree of MI distillation in terms normalized MI index. Our experimental results on the realistic LR face datasets substantiate that the MIND-Net instances assembled from the pre-learned CNNs stand out from the baselines and other state of the arts by a notable margin.

Biometric Cryptosystems for secret binding such as fuzzy vault and fuzzy commitment are provable secure and offers a convenient way for secret management and protection. Despite numerous practical schemes have been reported, they are deficient in resisting several security and privacy attacks. In this paper, we propose a novel bio-cryptosystem that based on the three key ingredients namely Index of Maximum (IoM) hashing, (m, k) threshold secret sharing and b-band mini vaults notion. The IoM hashing is motivated from the ranking based Locality Sensitive Hashing theory meant for non-invertible transformation. On the other hand, the (m, k) threshold secret sharing scheme and the b-band mini vaults manage overcome inherent limitations of biometric cryptosystems when integrated with IoM hashing. The proposed scheme strikes the balance between performance and the privacy/security protection. Unlike fuzzy vault and fuzzy commitment, which primarily devised for unordered and binary biometrics, respectively, our scheme is tailored for feature vector-based biometrics (vectorial biometrics). Comprehensive experiments on fingerprint vectors that derived from several FVC fingerprint benchmarks and rigorous analysis demonstrate decent secret retrieval performance yet offer strong resilience against six major security and privacy attacks.

Biometric cryptosystems such as fuzzy vaults represent one of the most popular approaches for secret and biometric template protection. However, they are solely designed for biometric verification, where the user is required to input both identity credentials and biometrics. Several practical questions related to the implementation of biometric cryptosystems remain open, especially in regard to biometric template protection. In this article, we propose a face cryptosystem for identification (FCI) in which only biometric input is needed. Our FCI is composed of a one-to-N search subsystem for template protection and a one-to-one match chaff-less fuzzy vault (CFV) subsystem for secret protection. The first subsystem stores N facial features, which are protected by index-of-maximum (IoM) hashing, enhanced by a fusion module for search accuracy. When a face image of the user is presented, the subsystem returns the top k matching scores and activates the corresponding vaults in the CFV subsystem. Then, one-to-one matching is applied to the k vaults based on the probe face, and the identifier or secret associated with the user is retrieved from the correct matched vault. We demonstrate that coupling between the IoM hashing and the CFV resolves several practical issues related to fuzzy vault schemes. The FCI system is evaluated on three large-scale public unconstrained face datasets (LFW, VGG2, and IJB-C) in terms of its accuracy, computation cost, template protection criteria, and security.

In this paper, we propose a data-driven cancellable biometrics scheme, referred to as SoftmaxOut Transformation-Permutation Network (SOTPN). The SOTPN is a neural version of Random Permutation Maxout (RPM) transform, which was introduced for facial template protection. We present a specialized SoftmaxOut layer integrated with the permutable MaxOut units and the parameterized softmax function to approximate the nondifferentiable permutation and the winner-takes-all operations in the RPM transform. On top of that, a novel pairwise ArcFace loss and a code balancing loss are also formulated to ensure that the SOTPN-transformed facial template is cancellable, discriminative, high entropy and free from quantization errors when coupled with the SoftmaxOut layer. The proposed SOTPN is evaluated on three face datasets, namely LFW, YouTube Face and Facescrub, and our experimental results disclosed that the SOTPN outperforms the RPM transform significantly.

Semi-supervised Learning (SSL) is a classical problem where a model needs to solve classification as it is trained on a partially labeled train data. After the introduction of generative adversarial network (GAN) and its success, the model has been modified to be applicable to SSL. ImprovedGAN as a representative model for GAN-based SSL, it showed promising performance on the SSL problem. However, the inner mechanism of this model has been only partially revealed. In this work, we revisit ImprovedGAN with a fresh look on it based on metric learning. In particular, we interpret ImprovedGAN by general pair weighting, a recent framework in metric learning. Based on this interpretation, we derive two theoretical properties of ImprovedGAN: (i) its discriminator learns to make confident predictions over real samples, (ii) the adversarial interaction in ImprovedGAN constrains the discriminator to decrease the angles between the features of real samples and class weight vectors. The two properties suggest that the adversarial interaction induces the class-wise cluster separation of the features as experimentally verified. Motivated by the findings, we propose a variant of ImprovedGAN, called Intensified ImprovedGAN, where its cluster separation characteristic is improved by two proposed techniques: (a) the unsupervised discriminator loss is scaled up and (b) the generated batch size is enlarged. As a result, I2GAN produces better class-wise cluster separation and, hence, generalization. Extensive experiments on the widely known benchmark data sets verify the effectiveness of our proposed method, showing that its performance is better than or comparable to other GAN based SSL models.

In one-class novelty detection, a model learns solely on the in-class data to single out out-class instances. Autoencoder (AE) variants aim to compactly model the in-class data to reconstruct it exclusively, thus differentiating the in-class from out-class by the reconstruction error. However, compact modeling in an improper way might collapse the latent representations of the in-class data and thus their reconstruction, which would lead to performance deterioration. Moreover, to properly measure the reconstruction error of high-dimensional data, a metric is required that captures high-level semantics of the data. To this end, we propose Discriminative Compact AE (DCAE) that learns both compact and collapse-free latent representations of the in-class data, thereby reconstructing them both finely and exclusively. In DCAE, (a) we force a compact latent space to bijectively represent the in-class data by reconstructing them through internal discriminative layers of generative adversarial nets. (b) Based on the deep encoder's vulnerability to open set risk, out-class instances are encoded into the same compact latent space and reconstructed poorly without sacrificing the quality of in-class data reconstruction. (c) In inference, the reconstruction error is measured by a novel metric that computes the dissimilarity between a query and its reconstruction based on the class semantics captured by the internal discriminator. Extensive experiments on public image datasets validate the effectiveness of our proposed model on both novelty and adversarial example detection, delivering state-of-the-art performance.

Periocular biometric covering the immediate vicinity of human eye is a synergistic alternative to face particularly when the face is masked or occluded. Most present work for periocular recognition in the wild are mainly convolutional neural networks learned based on cross-entropy loss. However, periocular images only capture the least salient face features, and thus suffering from severe intra-class compactness and inter-class dispersion issues for discriminative deep feature learning. Recently, label smoothing regularization (LSR) is discerned capable of diminishing the intra-class variation by minimizing the Kullback-Liebler divergence of a uniform distribution and a network prediction distribution. In this letter, we extend LSR to that of Generalized LSR (GLSR) by learning a pre-task network prediction, in place of the predefined uniform distribution. Extensive experiments on four periocular in the wild datasets disclose that the GSLR-trained networks prevail over the LSR-based counterpart and other most recent the state of the arts. This is supported by our empirical analyses that the embedding periocular features rendered by GLSR results in better class-wise cluster separation than the conventional LSR.

Stacking-based deep neural network (S-DNN) is aggregated with pluralities of basic learning modules, one after another, to synthesize a deep neural network (DNN) alternative for pattern classification. Contrary to the DNNs trained from end to end by backpropagation (BP), each S-DNN layer, that is, a self-learnable module, is to be trained decisively and independently without BP intervention. In this paper, a ridge regression-based S-DNN, dubbed deep analytic network (DAN), along with its kernelization (K-DAN), are devised for multilayer feature relearning from the pre-extracted baseline features and the structured features. Our theoretical formulation demonstrates that DAN/K-DAN relearn by perturbing the intra/interclass variations, apart from diminishing the prediction errors. We scrutinize the DAN/K-DAN performance for pattern classification on datasets of varying domains-faces, handwritten digits, generic objects, to name a few. Unlike the typical BP-optimized DNNs to be trained from gigantic datasets by GPU, we reveal that DAN/K-DAN are trainable using only CPU even for small-scale training sets. Our experimental results show that DAN/K-DAN outperform the present S-DNNs and also the BP-trained DNNs, including multiplayer perceptron, deep belief network, etc., without data augmentation applied.

In this paper, we propose a recursive learning formulation for online heterogeneous face recognition (HFR). The main task is to compare between images which are acquired from different sensing spectrums for identity recognition. Using an extreme learning machine, the proposed recursive formulation seeks a direct optimization to the classification error goal where the solution converges exactly to the batch mode solution. Due to the nonlinear nature of the classification error objective function, formulation of a recursive solution that converges is an important and nontrivial task. Based on this recursive formulation, an online HFR system is designed. The system is evaluated using two challenging heterogeneous face databases with images captured under visible, near infrared and infrared spectrums. The proposed system shows promising performance which is comparable with that of competing state-of-the-arts.

Touch-stroke dynamics is a relatively recent behavioral biometrics. It authenticates an individual by observing his behavior when swiping a “stroke” on a smartphone or tablet. Several studies have attempted to determine the optimum authentication accuracy of classifiers, but none of them has used time series or temporal machine learning techniques. We postulate that when a user performs a series of touch strokes in a continuous manner, it can be perceived as a temporal behavior characteristic of the person. In this letter, we propose the use of a temporal regression forest to unearth this hidden but vital temporal information. By incorporating this temporal information in the authentication process, the proposed model is able to achieve average equal error rates of ~4.0% and ~2.5% on the Serwadda dataset and Frank dataset, respectively.

This paper devises a new means of filter diversification, dubbed multi-fold filter convolution (M-FFC), for face recognition. On the assumption that M-FFC receives single-scale Gabor filters of varying orientations as input, these filters are selfcross convolved by M-fold to instantiate a filter offspring set. The M-FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA, and ICA filters thus yields three offspring sets: 1) Gabor filters solely; 2) Gabor-PCA filters; and 3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors. To facilitate a sensible Gabor filter selection for M-FFC, the 40 multi-scale, multi-orientation Gabor filters are condensed into eight elementary filters. Aside from that, an average histogram pooling operator is employed to leverage the 2-FFC histogram features, prior to the final whitening PCA compression. The empirical results substantiate that the 2-FFC descriptors prevail over, or on par with, other face descriptors on both identification and verification tasks.

Continuous authentication (CA) with touch stroke dynamics is an emerging problem for mobile identity management. In this paper, we focus on one of the essential problems in CA namely one-class classification problem. We propose a novel analytic probabilistic one-class classifier coined One-Class Random MaxOut Probabilistic Network (OC-RMPNet). The OC-RMPNet is a single hidden layer network that is tailored to capture individual users' touch-stroke profiles. The input-hidden layer of the network is meant to project the input vector onto the high dimensional random maxout feature space and the hidden-output layer acts as an OC probabilistic predictor that trained by means of least-square principle, hence require no iterative learning. We also put forward a feature sequential fusion mechanism for accuracy improvement. We scrutinize and compare the proposed methods with existing works on touchanalytics and HMOG datasets. The empirical results reveal that the OC-RMPNet prevails over its predecessor in touch-stroke authentication tasks on mobile phones.

Despite biometrics is deemed a more secure and user-friendly solution than password-based or token-based approach for identity management, biometric templates are vulnerable to adversary attacks that may lead to privacy invasion and irreversible identity theft. Cancelable biometrics is a template protection method that generates a noninvertible identifier from the original biometric template by means of a parameterized transformation function and user/application-specific parameters. However, the necessity to input parameter, either in possession (token) or in memory (password) form along with biometrics, hence two factors, jeopardizes usability of the biometrics. In this paper, we propose a one-factor cancellable biometric authentication scheme that empowered by Indexing First Order hashing, a tailor-made locality sensitive hashing function for template protection. We evaluate the proposed scheme with respect to four template protection design criteria, namely noninvertible, renewability, unlinkability and accuracy performance. We also analyze the threat model of the proposed scheme that enclosed five major security attacks. Despite the scheme can be applied to any binary biometric features, we adopt binary fingerprint vector as a case study for this paper. The evaluations have been carried out under six datasets taken from FVC 2002 and FVC 2004 benchmark databases.

Touch-stroke dynamics is an emerging behavioral biometrics justified feasible for mobile identity management. A touch-stroke dynamics authentication system is composed of a hand-engineered feature extractor and a classifier separately. In this letter, we propose a stacking-based deep learning network that performs feature extraction and classification, collectively dubbed Kernel Deep Regression Network (KDRN). The KDRN is built on multiple kernel ridge regressions (KRR) hierarchically, where each is trained analytically and independently. In principal, KDRN does not mean to learn directly from the raw touch-stroke data like other deep learning models, but it relearns from the pre-extracted features to yield a richer and a relatively more discriminative feature set. Subsequent to that, the authentication is carried out by KRR. Overall, KDRN achieves an equal error rate of 0.013% for intrasession authentication, 0.023% for intersession authentication, and 0.121% for interweek authentication on the Touchlaytics dataset.

In this paper, we propose a ranking-based locality sensitive hashing inspired two-factor cancelable biometrics, dubbed “Index-of-Max” (IoM) hashing for biometric template protection. With externally generated random parameters, IoM hashing transforms a real-valued biometric feature vector into discrete index (max ranked) hashed code. We demonstrate two realizations from IoM hashing notion, namely, Gaussian random projection-based and uniformly random permutation-based hashing schemes. The discrete indices representation nature of IoM hashed codes enjoys several merits. First, IoM hashing empowers strong concealment to the biometric information. This contributes to the solid ground of non-invertibility guarantee. Second, IoM hashing is insensitive to the features magnitude, hence is more robust against biometric features variation. Third, the magnitude-independence trait of IoM hashing makes the hash codes being scale-invariant, which is critical for matching and feature alignment. The experimental results demonstrate favorable accuracy performance on benchmark FVC2002 and FVC2004 fingerprint databases. The analyses justify its resilience to the existing and newly introduced security and privacy attacks as well as satisfy the revocability and unlinkability criteria of cancelable biometrics.

Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.

Stacking-based deep neural network (S-DNN), in general, denotes a deep neural network (DNN) resemblance in terms of its very deep, feedforward network architecture. The typical S-DNN aggregates a variable number of individually learnable modules in series to assemble a DNN-alike alternative to the targeted object recognition tasks. This work likewise devises an S-DNN instantiation, dubbed deep analytic network (DAN), on top of the spectral histogram (SH) features. The DAN learning principle relies on ridge regression, and some key DNN constituents, specifically, rectified linear unit, fine-tuning, and normalization. The DAN aptitude is scrutinized on three repositories of varying domains, including FERET (faces), MNIST (handwritten digits), and CIFAR10 (natural objects). The empirical results unveil that DAN escalates the SH baseline performance over a sufficiently deep layer.

The principal component analysis network (PCANet) is asserted as a parsimonious stacking-based convolutional neural networks (CNNs) instance for generic object recognition including face. However, to be regarded a CNN resemblance, PCANet lacks a nonlinearity in between two successive convolutional layers. The multilayer PCANet (by neglecting the nonlinearity pre-requisite) is also deemed far-fetched for the network depth beyond two, due to feature dimensionality explosion. We thus devise a PCANet alternative, dubbed PCANet+ in this letter, to untangle these constraints. To be more precise, conforming to the CNN essentials, PCANet+ conveys a mean-pooling unit manipulating each feature map. On top of that, we streamline the PCANet topology to permit a deep construction with an expanded PCA filter ensemble. We scrutinize the PCANet+ performance using face recognition technology and other two faces in the wild datasets, namely, labeled faces in the wild and YouTube faces. The experimental results reveal that the PCANet+ descriptor prevails over its predecessor and other stacking-based descriptors in face identification and verification, serving a baseline for ConvNets.

Gait recognition appears to be a valuable asset when conventional biometrics cannot be employed. Nonetheless, recognizing human by gait is not a trivial task due to the complex human kinematic structure and other external factors affecting human locomotion. A major challenge in gait recognition is view variation. A large difference between the views in the query and reference sets often leads to performance deterioration. In this paper, we show how to generate virtual views to compensate the view difference in the query and reference sets, making it possible to match the query and reference sets using standardized views. The proposed method, which combines multiview matrix representation and a novel randomized kernel extreme learning machine, is an end-to-end solution for view change problem under Grassmann manifold treatment. Under the right condition, the view-tagging problem can be eliminated. Since the recording angle and walking direction of the subject are not always available, this is particularly valuable for a practical gait recognition system. We present several working scenarios for multiview recognition that have not be considered before. Rigorous experiments have been conducted on two challenging benchmark databases containing multiview gait datasets. Experiments show that the proposed approach outperforms several state-of-the-arts methods.

The standard multi-scale, multi-orientation Gabor filter ensemble (SGFE) in the face recognition task reposits 40 filters localized in 8 orientations and 5 scales, with a real and an imaginary constituent. This paper devises a simple means of filter diversification, dubbed as multi-fold Gabor filter convolution (-FGFC), where a set of pre-selected filters, e.g., single-scale Gabor filters across varying orientations, are self-cross convolved by folds to instantiate the offspring filters. To facilitate filter selection for-FGFC, this paper summarizes SGFE into the condensed Gabor filter ensemble (CGFE) of only 8 filters. In addition, an average histogram pooling operator is proposed to downsample and regulate the demodulated Gabor phase features prior to the final compression stage. The performance of a specific M-FGFC instance, i.e., the 2-FGFC descriptor, is investigated on FERET I (frontal), FERET II (nonfrontal) and AR datasets. The experimental results on FERET I substantiates that the 2-FGFC descriptor outperforms the leading state of the art face descriptors.

Gabor-based region covariance matrix (GRCM) has been demonstrated as a promising descriptor for face recognition. However, GRCM requires large number of filters to achieve satisfactory performance. Furthermore, complex-valued Gabor filters require double convolution operations for each filter that makes the computation more expensive. To alleviate the problem, we propose to adopt real-valued discrete cosine transform (DCT) as filter bank in place of complex-valued Gabor filter. DCT as an orthogonal transform however decorrelates the signal, leads to most energies fall into the diagonal entries of the constructed covariance matrix, which is ill-formed for RCM. We demonstrate that applying non-linear operation on the DCT filter responses ameliorates the decorrelated filter responses effects. Apart from that, while RCM offers spatial information that is useful for recognition tasks, overly small RCM region renders poor covariance estimation, which can affect the recognition performance drastically. In this paper we also propose Log-TiedRank to mitigate the potential undersampling effect suffered by covariance matrix estimation. From the experiments Log-TiedRank shows surprising performance boost over AIRM and Log-Euclidean metric especially when both gallery set and probe set have very different distributions.

The ISO/IEC 19794-2-compliant fingerprint minutiae template is an unordered and variable-sized point set data. Such a characteristic leads to a restriction for the applications that can only operate on fixed-length binary data, such as cryptographic applications and certain biometric cryptosystems (e.g., fuzzy commitment). In this paper, we propose a generic point-to-string conversion framework for fingerprint minutia based on kernel learning methods to generate discriminative fixed length binary strings, which enables rapid matching. The proposed framework consists of four stages: (1) minutiae descriptor extraction; (2) a kernel transformation method that is composed of kernel principal component analysis or kernelized locality-sensitive hashing for fixed length vector generation; (3) a dynamic feature binarization; and (4) matching. The promising experimental results on six datasets from fingerprint verification competition (FVC)2002 and FVC2004 justify the feasibility of the proposed framework in terms of matching accuracy, efficiency, and template randomness.

Mobile devices have become an integral part of our routine activities. Some of the activities involve the storage or access of sensitive data (e.g. on-line banking, paperless prescription services, etc.). These mobile electronic services (e-Services) typically require a method to securely identify and authenticate a claimed identity. Currently, e-Services typically use a knowledge-based authentication method by demonstrating the knowledge of a secret (e.g. password), but it is vulnerable to a number of security attacks, e.g. shoulder spoofing and brute force attacks. To thwart the attacks and to make the authentication method more secure, this paper describes our efforts in investigating the benefits of integrating touch dynamics biometrics, into a PIN-based authentication method. It reports the collection of a comprehensive reference dataset from 150 subjects, the extraction of feature data from the dataset, and the classifications and the use of the feature data to identify a user. Experimental results show that, even when the PIN is exposed, 9 out of 10 impersonation attempts can be successfully detected.

In this paper, a single hidden-layer feedforward fusion network is proposed for face identity verification. Essentially, the feature extraction, matching score calculation and fusion algorithm design steps are integrated and absorbed into a hidden layer of the model. Each hidden node works on the raw face image directly and produces an Euclidean distance based match score within the network. These scores are then incorporated with output weights to produce a fused score at the final stage. Our experimental study conducted using three face databases shows that the proposed model consistently outperforms competing methods.

Gabor-based region covariance matrix (GRCM) is an emerging face feature descriptor, which has been shown promising for face recognition. The GRCM lies on Tensor manifold is inherently non-Euclidean, hence a disconnect exists between GRCM descriptor and vector-based classifiers, such as collaborative representation-based classifier (CRC). CRC is a strong alternative to sparse representation-based classifier yet enjoys high efficiency. In this paper, we bridge GRCM and CRC with kernel learning method. We investigate several geodesic distances on Tensor manifold that satisfy the Mercer's condition for kernel CRC construction as well as for speedy computation. Apart from that, we also devise two strategies to jointly combine the regionalized GRCMs with Tensor kernel CRC. Extensive experiments on the ORL and FERET datasets are conducted to verify the efficacy of the proposed method.

For a large-scale software system, especially an online service system, when a performance issue occurs, it is desirable to check whether this issue has occurred before. If there are past similar issues, a known remedy could be applied. Otherwise, a new troubleshooting process may have to be initiated. The symptom of a performance issue can be characterized by a set of metrics. Due to the sophisticated nature of software systems, manual diagnosis of performance issues based on metric data is typically expensive and laborious. In this paper, we propose a Hidden Markov Random Field (HMRF) based approach to automatic identification of recurrent and unknown performance issues. We formulate the problem of issue identification as a HMRF-based clustering problem. Our approach incorporates the learning of metric discretization thresholds and the optimization of issue clustering. Based on the learned thresholds and cluster centroids, we can achieve accurate identification of recurrent issues and unknown issues. Experimental evaluations on an open benchmark and a large-scale industrial production system show that our approach is effective and outperforms the related state-of-the-art approaches.

ABSTRACT With the massive deployment of biometric applications, protecting the biometric template has attracted great attention because of the privacy issue. Although many proposals on protecting biometric template have been reported in literature, design a method simultaneously satisfying four criteria, that is performance, non‐invertibility, cancellability, and diversity still remains unsolved. In this paper, we proposed a two‐dimensional random projected minutiae vicinity decomposition (MVD) technique to secure minutiae‐based fingerprint template. Minutiae vicinity is first formed from a set of fingerprint minutiae and further used to generate a set of local features, namely MVD features; then, a random matrix derived from user‐specific token is used to project MVD features for the concealment of the topology of MVD. Comprehensive experiments on fingerprint verification competition datasets are carried out, and the lowest equal error rate obtained in the stolen‐token scenario is 3.07% and 1.02% for fingerprint verification competition 2002 database 1 and database 2, respectively. Besides, detail analyses on the irreversibility, cancellability, template size, and computational cost have been carried out. Copyright © 2013 John Wiley & Sons, Ltd.

In this work, a dynamic handwritten signature verification system based on hybrid discrete wavelet transform and discrete Fourier transform is presented. Wavelet transform is adopted to analyze the signature information in a multi-resolution representation while retaining its local information by decomposing the signature into different sub-bands. Fourier transform is performed to extract the feature descriptor of the decomposed sub-bands. A dissimilarity score of the extracted features between the test signature and reference data is computed using Euclidean distance and enveloped Euclidean distance. Apart from that, several score level fusion mechanisms have been investigated to combine decisive information to boost up the system performance. The k-nearest neighbor and support vector machine are applied in order to fuse multiple features. The resulting score value is then normalized and compared with a threshold value in order to decide whether a given signature is genuine or forgery. Experiments are conducted on a released version of benchmark SVC2004 database. Two datasets (Task 1 and Task 2), which have different types of signature information, are used to evaluate the proposed system, and promising verification results are achieved.

ABSTRACT Biometric template security and privacy issues are critical in biometric authentication systems and require special attention. However, remote biometric authentication systems demand wider array of measures for maximum protection. This paper proposes a remote cancelable palmprint authentication protocol based on multi‐directional two‐dimensional PalmPhasor‐fusion. The main contribution is three‐fold. First, with a transposition direction selection mechanism, multi‐directional two‐dimensional PalmPhasor (MTDPP) improves the accuracy performance of two‐dimensional PalmPhasor. Second, we provide the theoretical analysis of the effect of transposition on the accuracy performance of two‐dimensional PalmPhasor, and hence establish an effective transposition direction range for the proposed MTDPP. Third, according to our analysis, the existing remote palmprint authentication system does not satisfy non‐invertibility criterion of secure template protection and is vulnerable to interception. Besides, secret message embedding as a countermeasure for database attacks deteriorates accuracy performance and causes inconvenience in updating authenticator. The proposed protocol uses multi‐directional two‐dimensional PalmPhasor‐fusion, one‐time random number encrypted with asymmetric cryptography and encrypted hash codes of MTDPP to address the problems. Copyright © 2013 John Wiley & Sons, Ltd.

One of the greatest challenges for gait recognition is identification across appearance change. In this paper, we present a gait recognition method called Sparse Grassmannian Locality Preserving Discriminant Analysis. The proposed method learns a compact and rich representation of the gait images through sparse representation. The use of Grassmannian locality preserving discriminant analysis further optimizes the performance by preserving both global discriminant and local geometrical structure of the gait data. Experiments demonstrate that the proposed method can tolerate variation in appearance for gait identification effectively.

Separability in a code is crucial in guaranteeing a decent Hamming-distance separation among the codewords. In multibit biometric discretization where a code is used for quantization-intervals labeling, separability is necessary for preserving distance dissimilarity when feature components are mapped from a discrete space to a Hamming space. In this paper, we examine separability of Binary Reflected Gray Code (BRGC) encoding and reveal its inadequacy in tackling interclass variation during the discrete-to-binary mapping, leading to a tradeoff between classification performance and entropy of binary output. To overcome this drawback, we put forward two encoding schemes exhibiting full-ideal and near-ideal separability capabilities, known as Linearly Separable Subcode (LSSC) and Partially Linearly Separable Subcode (PLSSC), respectively. These encoding schemes convert the conventional entropy-performance tradeoff into an entropy-redundancy tradeoff in the increase of code length. Extensive experimental results vindicate the superiority of our schemes over the existing encoding schemes in discretization performance. This opens up possibilities of achieving much greater classification performance with high output entropy.

ABSTRACT Recently, a few biometric identity‐based encryption (BIO‐IBE) schemes have been proposed. BIO‐IBE leverages both fuzzy extractor and Lagrange polynomial to extract biometric feature as a user public key and as a preventive measure of collusion attack, respectively. In this paper, we reveal that BIO‐IBE is not realistic whereby a query of fresh biometrics is needed for each encryption process. Moreover, the use of both fuzzy extractor and Lagrange polynomial in BIO‐IBE simultaneously is a redundancy; it confers no advantage, but simply computational overhead. Therefore, we amend the progression of the BIO‐IBE scheme by eliminating either Lagrange polynomial or fuzzy extractor to alleviate computational complexity. Subsequently, we demonstrate that the amendment does not compromise the security of the BIO‐IBE scheme. Such amendments can be applied to other BIO‐IBE schemes as well. Copyright © 2013 John Wiley & Sons, Ltd.

Biometric discretization is a key component in biometric cryptographic key generation. It converts an extracted biometric feature vector into a binary string via typical steps such as segmentation of each feature element into a number of labeled intervals, mapping of each interval-captured feature element onto a binary space, and concatenation of the resulted binary output of all feature elements into a binary string. Currently, the detection rate optimized bit allocation (DROBA) scheme is one of the most effective biometric discretization schemes in terms of its capability to assign binary bits dynamically to user-specific features with respect to their discriminability. However, we learn that DROBA suffers from potential discriminative feature misdetection and underdiscretization in its bit allocation process. This paper highlights such drawbacks and improves upon DROBA based on a novel two-stage algorithm: 1) a dynamic search method to efficiently recapture such misdetected features and to optimize the bit allocation of underdiscretized features and 2) a genuine interval concealment technique to alleviate crucial information leakage resulted from the dynamic search. Improvements in classification accuracy on two popular face data sets vindicate the feasibility of our approach compared with DROBA.

ABSTRACT Fuzzy identity‐based identification (FIBI) scheme is a recently proposed cryptographic identification protocol. The scheme utilizes user biometric trait as public keys. The authentication is deemed success in the presence of the genuine query biometric together with the valid private key. Because of the fuzziness nature of biometrics, FIBI does not correct the errors on the query biometric with respect to the public key; instead, it tolerates the errors using Lagrange polynomial interpolation. Therefore, FIBI requires the biometric trait to be represented in a discrete (binary or integer) array that is fixed in length. In this paper, we report the first realization of FIBI scheme by means of fingerprint biometrics using minutia representation where our technique integrates the security features of both biometric and cryptography effectively. The simulation shows that the entire protocol can be completed within 1 s where false acceptance rate (FAR) = 0% and false reject rate (FRR) = 0.25% in FVC2002 DB1, and FAR = 0% and FRR = 0.125% in FVC2002 DB2. Our integration technique may also be applied on other fuzzy identity‐based cryptosystems. Copyright © 2012 John Wiley & Sons, Ltd.

Biometric discretization derives a binary string for each user based on an ordered set of real-valued biometric features. The false acceptance rate (FAR) and the false rejection rate (FRR) of a binary biometric-based system significantly relies on a Hamming distance threshold which decides whether the errors in the query bit string will be rectified with reference to the template bit string. Kelkboom have recently modeled a basic framework to estimate the FAR and the FRR of one-bit biometric discretization. However, as the demand of a bit string with higher entropy (informative length) rises, single-bit discretization is getting less useful today due to its incapability of producing bit string that is longer than the total feature dimensions being extracted, thus causing Kelkboom's model to be of restricted use. In this paper, we extend the analytical framework to multibit discretization for estimating the performance and the decision threshold for achieving a specified FAR/FRR based on equal-probable quantization and linearly separable subcode encoding. Promising estimation results on a synthetic data set with independent feature components and Gaussian measurements vindicate the analytical expressions of our framework. However, for experiments on two popular face data sets, deviation in estimation results were obtained mainly due to the mismatch of independency assumption of our framework. We hence fit the analytical probability mass functions (pmfs) to the experimental pmfs through estimating the mean and the variance parameters from the difference between the corresponding analytical and experimental curves to alleviate such estimation inaccuracies on these data sets.

Minutia vicinity representation was recently proposed by Yang & Busch to generate a protected fingerprint template scheme [14], the resultant protected template enjoys good accuracy and free from alignment. However, Yang and Busche 's scheme is highly likely reversible [18]. This paper proposed a new minutiae representation technique known as Minutia Vicinity Decomposition (MVD) whereby each minutia vicinity is decomposed into four minutia triplets. A set of geometrical invariant features can be extracted from the minutia triplet to construct a fingerprint template. The invariant features with random offsets salting mechanism enhance the reversibility, revocability as well as performance accuracy of the resultant protected fingerprint template. Promising experimental results on FVC2002 DB2 justify the feasibility of our proposed technique.

Biometrie discretization converts extracted biométrie features into a binary string via a process of segmenting every one-dimensional feature space into possibly distinct multiple intervals and encoding every interval-captured feature element correspondingly. Eventually, the individual binary output of every feature element is concatenated into a binary string. To the best of our knowledge, Detection Rate Optimized Bit Allocation (DROBA) scheme is currently the most effective biométrie quantization scheme, offering its capability in assigning bits dynamically for each user-specific feature. However, we discover that DROBA suffers from potential discriminative feature miss-detections and under-quantized conditions. This paper highlights such drawbacks and improves upon DROBA by incorporating a dynamic searching method to efficiently recapture such miss-detected features. Experimental results illustrating significant improvements in classification accuracy justify the practicality of our approach.

This paper presents an innovative contactless palm print and palm vein recognition system. We design a hand sensor that could capture the palm print and palm vein image using low-resolution web camera. Both the visible and infrared images can be captured at the same time, and we do not need specialized infrared sensor to image the vein pattern. The design of the device is simple and low-cost. The subject can be shielded completely from the complication of undergoing two separate acquiring processes. We allow subjects to position their hands freely above the sensor and they can move their hands during the acquisition process. In order to obtain clear image of the palm vascular pattern, we propose a novel image enhancement technique called local-ridge-enhancement (LRE). The proposed method removes illumination error while keeping good contrast between the print/vein pattern and the background image. Besides, we introduce a simple yet robust directional coding technique to encode the palm print and palm vein features in bit string representation. The bit string representation offers speedy template matching and enables more effective template storage and retrieval. The scores output by the palm print and palm vein experts are fused using Support Vector Machine. The fusion of these features yields promising result for practical implementation.

Performance of a face recognition system has not been satisfied due to the illumination variation on facial image. Thus, there were many works that dealing with illumination compensation in face recognition in the past decades. One of the important techniques is to remove the illumination component based on the illumination reflectance model. In this paper, a facial image illumination invariant algorithm is devised based on the fusion of wavelet analysis and local binary pattern. The algorithm first removes the coefficients in logarithm wavelet approximation subband to get rid of illumination component. Next, reflectance component of facial image is then enhanced through the mapping of local binary pattern histogram. Finally, two processed images are combined through wavelet image fusion. Experiment results show that the proposed technique is promising in achieving the illumination invariant for facial images.

Neighborhood Preserving Embedding (NPE) is an unsupervised linear dimensionality reduction technique which attempts to solve the “out of sample” problem in Locally Linear Embedding (LLE). This is done by introducing a linear transform matrix into LLE, and hence NPE can be perceived as a linear approximation to LLE. In this paper, we modify the original NPE for face recognition by embedding prior class information in the process of neighborhood selection. Intuitively, neighboring points are kept intact if they have the same class label, while avoid points of other classes from entering the neighborhood. We proved experimentally in three face databases, ie. ORL, PIE and FRGC, and with comparisons with other linear and non-linear feature extractors, the intuition underlying the inclusion of class information in NPE works out very advantageously for achieving high recognition performance.

Traditional biometrics recognition system is vulnerable to privacy invasion when the stored biometric template is compromised. This in turn will suffer from permanently loss as biometric template is not replaceable In this paper, we propose a key extraction scheme which locks a secure transformed fingerprint bitstring via a novel dynamic quantization mechanism. During authentication stage, the key is extracted from the secure mixture when a genuine fingerprint is presented. A number of keys can be assigned to different applications and could be revoked if the key was compromised. The proposed method retrieve key reliably from a genuine fingerprint up to 99.5% success rate. We perform several security and experimental analyses and the results suggest that the scheme is feasible in practice.

Purpose This paper aims to address some of the practical and security problems when using fingerhash to secure biometric key for protecting digital contents. Design/methodology/approach Study the two existing directions of biometric‐based key generation approach based on the usability, security and accuracy aspects. Discuss the requisite unresolved issues related to this approach. Findings The proposed Fingerhashing approach transforms fingerprint into a binary discretized representation called Fingerhash. The Reed Solomon error correction method is used to stabilize the fluctuation in Fingerhash. The stabilized Fingerhash is then XORed with a biometric key. The key can only be released upon the XOR process with another Fingerhash derived from an authentic fingerprint. The proposed method could regenerate an error‐free biometric key based on an authentic fingerprint with up to 99.83 percent success rate, leading to promising result of FAR = 0 percent and FRR = 0.17 percent. Besides, the proposed method can produce biometric keys (1,150 bit length) which are longer in size than the other prevailing biometric key generation schemes to offer higher security protection to safeguard digital contents. Originality/value Outlines a novel solution to address the issues of usability, security and accuracy of biometric based key generation scheme.

Biometric characteristics cannot be changed; therefore, the loss of privacy is permanent if they are ever compromised. This paper presents a two-factor cancelable formulation, where the biometric data are distorted in a revocable but non-reversible manner by first transforming the raw biometric data into a fixed-length feature vector and then projecting the feature vector onto a sequence of random subspaces that were derived from a user-specific pseudorandom number (PRN). This process is revocable and makes replacing biometrics as easy as replacing PRNs. The formulation has been verified under a number of scenarios (normal, stolen PRN, and compromised biometrics scenarios) using 2400 Facial Recognition Technology face images. The diversity property is also examined.

Reliable touch-less fingerprint recognition still remains a challenge nowadays as the conventional techniques that used to preprocess the optical or capacitance sensor acquired fingerprint image, for segmentation, enhancement and core point detection, are inadequate to serve the purpose. The problems of the touch-less fingerprint recognition are the low contrast between the ridges and the valleys in fingerprint images, defocus and motion blur. However, it imposes a competency for a further advancing of this biometric modality since it frees from the problems in terms of hygienic, maintenance and latent fingerprints. In this paper, the digital camera is opted as the device to capture the fingerprint image in RGB format and the procedures to segment, enhance and detect the core point of the fingerprint image are outlined

Biometrics characteristics are immutable, resulting in permanent biometrics compromise. To address this problem, we prescribe a generic cancellable biometrics formulation - BioPhasor. BioPhasor is a set of binary code based on iterated mixing between the user-specific tokenised pseudo-random number and the biometric feature. This method enables straightforward revocation of biometric template via token replacement. The transformation is non-invertible and BioPhasor able to achieve extremely low error rate compare to sole biometrics in verification setting. The privacy invasion and non-revocable problems in biometrics could be resolved by revocation of resulting feature through the pseudo-random number replacement. We also consider an unfavorable scenario in which an imposter has access genuine token and used by the imposter to claim as the genuine user. The feasibility of the formulation is demonstrated by the experiments on fingerprint images from the FVC2004 database

Biometric analysis for identity verification is becoming a widespread reality. Such implementations necessitate large-scale capture and storage of biometric data, which raises serious issues in terms of data privacy and (if such data is compromised) identity theft. These problems stem from the essential permanence of biometric data, which (unlike secret passwords or physical tokens) cannot be refreshed or reissued if compromised. Our previously presented biometric-hash framework prescribes the integration of external (password or token-derived) randomness with user-specific biometrics, resulting in bitstring outputs with security characteristics (i.e., noninvertibility) comparable to cryptographic ciphers or hashes. The resultant BioHashes are hence cancellable, i.e., straightforwardly revoked and reissued (via refreshed password or reissued token) if compromised. BioHashing furthermore enhances recognition effectiveness, which is explained in this paper as arising from the Random Multispace Quantization (RMQ) of biometric and external random inputs.

In this paper, we describe a biometric hash algorithm for robust extraction of bits from face images. While a face-recognition system has high acceptability, its accuracy is low. The problem arises because of insufficient capability of representing features and variations in data. Thus, we use dimensionality reduction to improve the capability to represent features, error correction to improve robustness with respect to within-class variations, and random projection and orthogonalization to improve discrimination among classes. Specifically, we describe several dimensionality-reduction techniques with biometric hashing enhancement for various numbers of bits extracted. The theoretical results are evaluated on the FERET face database showing that the enhanced methods significantly outperform the corresponding raw methods when the number of extracted bits reaches 100. The improvements of the postprocessing stage for principal component analysis (PCA), Wavelet Transform with PCA, Fisher linear discriminant, Wavelet Transform, and Wavelet Transform with Fourier-Mellin Transform are 98.02%, 95.83%, 99.46%, 99.16%, and 100%, respectively. The proposed technique is quite general, and can be applied to other biometric templates. We anticipate that this algorithm will find applications in cryptographically secure biometric authentication schemes.