The primary obstacle in realizing the full potential of finger crease biometrics is the accurate identification of deformed knuckle patterns, often resulting from completely contactless imaging. Current methods struggle significantly with this task, yet accurate matching is crucial for applications ranging from forensic investigations, such as child abuse cases, to surveillance and mobile security. To address this challenge, our study introduces the largest publicly available dataset of deformed knuckle patterns, comprising 805,768 images from 351 subjects. We also propose a novel framework to accurately match knuckle patterns, even under severe pose deformations, by recovering interpretable knuckle crease keypoint feature templates. These templates can dynamically uncover graph structure and feature similarity among the matched correspondences. Our experiments, using the most challenging protocols, illustrate significantly outperforming results for matching such knuckle images. For the first time, we present and evaluate a theoretical model to estimate the uniqueness of 2D finger knuckle patterns, providing a more interpretable and accurate measure of distinctiveness, which is invaluable for forensic examiners in prosecuting suspects.

This paper addresses two key challenges in detecting diffusion-model generated videos: generalization to unseen but sophisticated video synthesizers and threats from the multimodal manipulations where the deepfakes combine the text prompts and visual synthesis to create realistic forgeries. We propose a novel multimodal framework built on a transformer-based architecture, which was originally designed for image forgery detection. Our framework extends this architecture by integrating two complementary components: (i) spatio-temporal feature extraction and (ii) a text-guided enrichment module which uses a frozen Vision Language Models (VLMs) text encoder when prompts are available and a small set of learnable default embeddings when no prompt is provided. Trained on our self-curated dataset comprising KlingAI and StableDiffusion Samples, we present cross-dataset performance from unseen but hyper-realistic fake video generators comprising Sora, Luma, Pika, and Runway. Our model can achieve high accuracy and outperformance results, which demonstrate cross-model generalization for detecting hyper-realistic AI-generated videos.

The remarkable progress in neural-network-driven visual data generation, especially with neural rendering techniques like Neural Radiance Fields and 3D Gaussian splatting, offers a powerful alternative to GANs and diffusion models. These methods can generate high-fidelity images and lifelike avatars, highlighting the need for robust detection methods. However, the lack of any large dataset containing images from neural rendering methods becomes a bottleneck for the detection of such sophisticated fake images. To address this limitation, we introduce NeuroRenderedFake, a comprehensive benchmark for evaluating emerging fake image detection methods. Our key contributions are threefold: (1) A large-scale dataset of fake images synthesized using state-of-the-art neural rendering techniques, significantly expanding the scope of fake image detection beyond generative models; (2) A cross-domain evaluation protocol designed to assess the domain gap and common artifacts between generative and neural rendering-based fake images; and (3) An in-depth spectral energy analysis that reveals how frequency domain characteristics influence the performance of fake image detectors. We train representative detectors, based on spatial, spectral, and multimodal architectures, on fake images generated by both generative and neural rendering models. We evaluate these detectors on 15 groups of fake images synthesized by cutting-edge neural rendering models, generative models, and combined methods that can exhibit artifacts from both domains. Additionally, we provide insightful findings through detailed experiments on degraded fake image detection and the impact of spectral features, aiming to advance research in this critical area.

Contactless 3D fingerprint identification systems have emerged to provide more accurate and hygienic alternatives to contact-based conventional systems that acquire hundreds of millions of fingerprints everyday. However, the intricate process of acquiring 3D fingerprints presents a significant challenge, acting as a key barrier to fully unlocking the potential of 3D fingerprint biometrics. This paper introduces a novel framework to directly recover corresponding 3D minutiae template from a single contactless 2D fingerprint image. Billions of contact-based fingerprints have been acquired and employed everyday for e-governance and other applications. Seamless adoption of contactless 3D fingerprint technologies also requires advanced capabilities to accurately match 3D fingerprints with respective 2D fingerprint templates, which is currently missing in existing literature. We therefore introduce novel capabilities to accurately align minutiae templates in 3D spaces and enable compensation for the unknown perspective transformation. This capability significantly enhances the ability to accurately match 3D to 3D and 3D to 2D fingerprint templates. Furthermore, we introduce a new approach to synthesizing realistic contactless fingerprint images, resulting in the generation of a large synthetic database complete with corresponding 3D ground truths of minutiae points. Finally, we provide a detailed theoretical analysis of formulation for the uniqueness of recovered 3D minutiae templates, providing a theoretical justification for the superiority of such 3D minutiae templates over their 2D counterparts.

We comment on a recently published TPAMI paper presenting an iris recognition algorithm. While the approach is intriguing, we have identified several inconsistencies and errors in this paper. Additionally, their comparison with the state-of-the-art methods lacks fairness. We take this opportunity to clarify and underline these errors, aiming to assist fellow researchers like us who are interested in advancing biometrics research.

The uniqueness of many biometric modalities can be attributed to the fine-grained and randomly textured patterns that are revealed in respective normalized images. This paper introduces a new approach to accurately match such biometric images using micropattern exemplars. The images acquired using different sensors, or spectrum, from the same biometric surface often reveal localized fine-grained micropatterns that maintain high similarity in such differently sensed images. Therefore, selecting appropriate micropattern exemplars that can encode similar micropatterns in both images is expected to enhance cross-sensor matching capabilities. We introduce specialized masks that are designed to efficiently encode such microstructural patterns for more accurate biometric identification. Our experiments specifically focus on the cross-modal palm patterns and introduce micropattern exemplars to match such biometric features more accurately. The experimental results presented on multiple public and fine-grained biometrics databases validate the effectiveness of the proposed approach in characterizing micro patterns that are retained in the images from different sensors. These results are highly encouraging and validate the effectiveness of the proposed approach for cross-sensor and cross-spectral biometrics identification. Our micropattern exemplars-based approach is quite generalized, and we present reproducible experiments on other biometric databases, from iris and knuckle, to underline its potential for a range of other biometric modalities.

Every day, billions of fingerprint images are captured worldwide through the extensive deployment of slap-fingerprint acquisition devices, serving e-governance programs and bolstering national border security. Several studies from national ID programs, like UIDAI and NIST, have indicated that about 2% of the user population may lack usable fingerprints. Finger knuckle patterns are inherently presented during such slap-fingerprint acquisition and can be simultaneously acquired without imposing any additional inconvenience on the users. Leveraging these finger knuckle patterns can enable not only significant improvement in identification accuracy but also enhance overall protection and facilitates smoother traffic flow. This paper develops the first such finger-knuckle-assisted fingerprint identification system for real-world applications. We systematically develop automated finger knuckle detection and segmentation algorithms, for multiple knuckles and under complex illumination, for such contactless images from the deployed slap fingerprint devices. Currently, available algorithms offer limited performance for such images, and therefore this paper proposes a new approach to more accurately match such knuckle images. Our experimental results illustrate the significant performance improvement over existing knuckle matching algorithms, and further by incorporating dynamic fusion capabilities. This paper also introduces the first joint finger-knuckle and fingerprint database, from 120 different subjects, in the public domain to advance further research and development efforts needed in this area.

Most recent methods formulate the task of human pose estimation as a heatmap estimation problem, and use the overall L2 loss computed from the entire heatmap to optimize the heatmap prediction. In this paper, we show that in bottom-up human pose estimation where each heatmap often contains multiple body joints, using the overall L2 loss to optimize the heatmap prediction may not be the optimal choice. This is because, minimizing the overall L2 loss cannot always lead the model to locate all the body joints across different sub-regions of the heatmap more accurately. To cope with this problem, from a novel perspective, we propose a new bottom-up human pose estimation method that optimizes the heatmap prediction via minimizing the distance between two characteristic functions respectively constructed from the predicted heatmap and the groundtruth heatmap. Our analysis presented in this paper indicates that the distance between these two characteristic functions is essentially the upper bound of the L2 losses w.r.t. sub-regions of the predicted heatmap. Therefore, via minimizing the distance between the two characteristic functions, we can optimize the model to provide a more accurate localization result for the body joints in different sub-regions of the predicted heatmap. We show the effectiveness of our proposed method through extensive experiments on the COCO dataset and the CrowdPose dataset.

Billions of contact-based fingerprint images have been acquired in large databases. Contactless 2D fingerprint identification systems have emerged to provide more hygienic and secured alternatives and are highly sought under the current pandemic. The success of such an alternative requires high match accuracy, not just for the contactless-to-contactless but also for the contactless-to-contact-based matching, which is currently below expectations for large-scale deployments. We introduce a new approach to advance such expectations on match accuracy and also to address privacy-related concerns, e.g., recent GDPR regulations, in the acquisition of very large databases. This paper introduces a novel approach for accurately synthesizing multi-view contactless 3D fingerprints to develop a very large-scale multi-view fingerprint database, and corresponding contact-based fingerprint database. A unique advantage of our approach is the simultaneous availability of much-needed ground truth labels and alleviation of laborious and often prone to erroneous tasks performed by human labeling. We also introduce a new framework that can not only accurately match contactless to contact-based images but also contactless to contactless images, as both of these capabilities are simultaneously required to advance contactless fingerprint technologies. Our rigorous experimental results presented in this paper, both for within-database and cross-database experiments, illustrate outperforming results to simultaneously meet both of these expectations and validate the effectiveness of the proposed approach.

Contactless palmprint identification offers significantly improved hygiene and user convenience, making it highly attractive for a range of civilian applications, especially during the current pandemic. However, the accurate recognition of contactless palmprint images can be highly challenging, attributed to the significant variations in the intra-class similarity and limitations of conventional palmprint feature descriptors under involuntary or contactless imaging variations. State-of-the-art completely contactless palmprint matching algorithms in the literature cannot adequately address these challenges and are not sufficiently accurate and fast enough for such real-world applications. This paper proposes a novel approach that adaptively locates the local palmprint regions with high similarities between their corresponding feature representations or templates to address these challenges. We consider spatial localization of such highly similar feature representations from multiple local regions and consolidate them to generate a more reliable match score. This paper presents reproducible and comparative experimental results, using within-database, cross-database, and cross-sensor performance evaluation, on four publicly available contactless palmprint datasets, including a sizeable contactless palmprint database from 600 different subjects. The proposed method achieves outperforming results compared with three state-of-the-art deep learning-based methods and five widely used conventional methods. In addition, the proposed method is also significantly faster than all state-of-the-art baseline methods .

Billions of fingerprint images are acquired and matched to protect the national borders and in a range of egovernance applications. Fast and accurate minutiae detection from fingerprint images is the key to advance fingerprint matching algorithms for large-scale applications. However, currently available fingerprint minutiae extraction methods are not accurate and fast enough to support such large-scale applications. This paper proposes a new method that uses a lightweight pixelwise local dilated neural network to extract local features and a patch-wise global neural network to recover the global features. It consolidates the local and global fingerprint features to generate a full-size minutiae location map, and then accurately localizes the minutiae positions by using a recursive connected components algorithm. We design a new loss function to accurately detect minutia orientation and incorporate a dynamic end-to-end loss to provide effective supervision in learning discriminant features. It is due to the proposed design and loss function that can enable higher accuracy with significantly less computations. We present reproducible experimental results from five publicly available contact-based and contactless databases that indicate significant improvement in the minutiae detection accuracy, which also leads to enhanced fingerprint matching accuracy. Since the minutiae represent key points in the fingerprint images, the proposed end-to-end minutiae detection method also has a potential to be employed in many other key points detection tasks.

Accurate detection of the fake but photorealistic images is one of the most challenging tasks to address social, biometrics security and privacy related concerns in our community. Earlier research has underlined the existence of spectral domain artifacts in fake images generated by powerful generative adversarial network (GAN) based methods. Therefore, a number of highly accurate frequency domain methods to detect such GAN generated images have been proposed in the literature. Our study in this paper introduces a pipeline to mitigate the spectral artifacts. We show from our experiments that the artifacts in frequency spectrum of such fake images can be mitigated by proposed methods, which leads to the sharp decrease of performance of spectrum-based detectors. This paper also presents experimental results using a large database of images that are synthesized using BigGAN, CRN, CycleGAN, IMLE, Pro-GAN, StarGAN, StyleGAN and StyleGAN2 (including synthesized high resolution fingerprint images) to illustrate effectiveness of the proposed methods. Furthermore, we select a spatial-domain based fake image detector and observe a notable decrease in the detection performance when proposed method is incorporated. In summary, our insightful analysis and pipeline presented in this paper cautions the forensic community on the reliability of GAN-generated fake image detectors that are based on the analysis of frequency artifacts as these artifacts can be easily mitigated.

Contactless 3D finger knuckle pattern is a new biometric identifier which offers highly discriminative features for the finger knuckle based personal identification. State-of-the-art methods for object recognition, a more generic problem, employ deep neural network based approaches and demonstrate superior effectiveness. However, any direct applications from those methods do not outperform specialized hand-crafted feature description approaches for the problem addressed in this paper. In addition, such deep neural network based methods have to address challenges associated with emerging biometrics, e.g. availability of very limited training data, large intra-class or train-test sample variations as observed for the real applications, etc. This paper attempts to address the above challenges and introduces a new deep neural network based approach for the contactless 3D finger knuckle identification. Our approach simultaneously encodes and incorporates deep features from multiple scales to form a more robust deep feature representation. Such collaborative feature representations are robustly matched using an efficient alignment scheme with a fully convolutional architecture to accommodate involuntary finger variations during the contactless imaging. Comparative experimental results in the two-session 3D finger knuckle images database, acquired from over 200 subjects and is publicly introduced from this paper, illustrate superior performance over the state-of-the-art methods, e.g. offering ~22% GAR improvement at extremely low FAR under challenging comparison scenarios. Additional experiments in other publicly available databases including 3D palmprint, 3D fingerprint, and 2D finger knuckle further validate the effectiveness and demonstrate the generalizability of the proposed approach.

Interoperability between contactless and conventional contact-based fingerprint recognition systems is fundamental for the success of emerging contactless fingerprint technologies which are highly sought, especially due to current pandemic. However, image formation differences and acquisition distortions between these two modalities pose significant challenges for such interoperability. In order to address these challenges, this paper presents a minutiae attention network with Siamese architecture and the reciprocal distance loss function to enable more accurate contactless to contact-based fingerprint identification. The proposed network contains two branches, a global-net branch to recover global features and a minutiae attention branch that focuses on the local minutiae areas. Attention mechanism is introduced to guide the minutiae attention branch to concentrate on distorted areas and recover minutiae/features correspondence for contactless and contact-based fingerprint images from the same fingers. Meanwhile, reciprocal distance loss is specifically designed to impose strong penalty towards contactless and contact-based fingerprint images from different fingers and guide the network to learn robust features for distinguishing identities. Experimental results on two publicly available databases illustrate significant performance improvements, over state-of-art methods in the literature, and validate the effectiveness of the proposed framework for the contactless to contact-based fingerprint identification.

Iris recognition has emerged as one of the most accurate and convenient biometric for person identification and has been increasingly employed in a wide range of e-security applications. The quality of iris images acquired at-a-distance or under less constrained imaging environments is known to degrade the iris recognition accuracy. The periocular information is inherently embedded in such iris images and can be exploited to assist in the iris recognition under such non-ideal scenarios. Our analysis of such iris templates also indicates significant degradation and reduction in the region of interest, where the iris recognition can benefit from a similarity distance that can consider importance of different binary bits, instead of the direct use of Hamming distance in the literature. Periocular information can be dynamically reinforced, by incorporating the differences in the effective area of available iris regions, for more accurate iris recognition. This article presents such a periocular-assisted dynamic framework for more accurate less-constrained iris recognition. The effectiveness of this framework is evaluated on three publicly available iris databases using within-dataset and cross-dataset performance evaluation, e.g., improvement in the recognition accuracy of 22.9%, 10.4% and 14.6% on three databases under both the verification and recognition scenarios.

Contactless 3D hand biometrics offers hygienic and convenient approaches for biometric recognition. This paper investigates a distinctive feature representation using 3D surface normal information for more accurate 3D hand biometric identification. Prior research on contactless 3D hand biometric identification largely incorporates 3D depth and surface curvature information to recover discriminative features. Our investigation presented in this paper indicates that extracting distinctive features from surface normal information, which can also be directly obtained from low-cost photometric stereo based imaging systems, can offer a computationally simpler alternative and is therefore highly desirable. The directions of neighbouring surface normal vectors can encode frequently observed irregular ridge and valley regions, which can enable more accurate surface feature description. Comparative experimental results presented in this paper validates the effectiveness of the proposed approach.

Study on finger knuckle patterns has attracted increasing attention for the automated biometric identification. However, finger knuckle pattern is essentially a 3D biometric identifier and the usage or availability of only 2D finger knuckle databases in the literature is the key limitation to avail full potential from this biometric identifier. This paper therefore introduces (first) contactless 3D finger knuckle database in public domain, which is acquired from 130 different subjects in two-session imaging using photometric stereo approach. This paper investigates on the 3D information from the finger knuckle patterns and introduces a new feature descriptor to extract discriminative 3D features for more accurate 3D finger knuckle matching. An individuality model for the proposed feature descriptor is also presented. Comparative experimental results using the state-of-the-art feature extraction methods on this challenging 3D finger knuckle database validate the effectiveness of our approach. Although our feature descriptor is designed for 3D finger knuckle patterns, it is also attractive for other hand-based biometric identifiers with similar patterns such as the palmprint and fingerprint. This observation is validated from the outperforming results, using the state-of-the-art pixel-wise 3D palmprint and 3D fingerprint feature descriptors, on other publicly available datasets.

Contactless fingerprint identification offers significantly higher user convenience, hygiene and has attracted increasing attention for the deployments. However, the presentation of fingers towards the contactless fingerprint sensors is hard to control and often results in unwanted pose changes that significantly degrade the contactless fingerprint matching accuracy. In order to address such problems and improve the fingerprint matching accuracy, this paper proposes a more precise minutiae extraction and pose-compensation approach. As compared with the conventional minutiae extraction approaches, our deep neural network-based approach does not require any image enhancement and is robust to spurious minutiae. All the minutiae extracted from our network are subjected to a three stage pose compensation framework: a) view angle estimation based on the location of core point, b) ellipsoid model formulation which simulates and compensate finger pose, c) intersection area estimation and alignment between different view angles. The proposed ellipsoid model is adaptive to both the silhouette of 2D contactless fingerprint image and the estimated view angle. The corresponding area between the different view angles can be theoretically estimated using this model and incorporated to align two contactless fingerprints for achieving superior matching accuracy. Our reproducible experimental results presented in this paper using public databases, and a database acquired during this work, validate the effectiveness of the proposed framework over the commercial software and earlier methods.

Contactless 3D finger knuckle is a new biometric identifier with a lot of potentials, which can provide an accurate, efficient and convenient alternative for the personal identification. The current 3D finger knuckle recognition methods are limited by computationally complex or inefficient matching algorithms, which attempt to compute the matching scores from all possible translational and rotational parameters for matching a pair of templates. The strength of such approach lies in its simplicity and reliability for accurately matching intra-class samples, but expensive computational time is required. Furthermore, attempting on excessive numbers of translational and rotational parameters can also degrade the overall recognition accuracy because the imposter matches can be increased. In fact, this conventional matching approach is commonly adopted in many biometric studies, but its drawbacks have not received adequate attention. This paper addresses such 3D finger knuckle recognition problem by developing a more efficient matching approach using surface key points extracted from 3D finger knuckle surfaces. Our comparative experimental results with the state-of-the art method on a publicly available 3D finger knuckle database indicates that our approach can offer over 23 times faster with performance improvement on the accuracy. Although the focus of our work is on 3D finger knuckle recognition, we also present the performance of our method on other publicly available databases with similar 3D biometric patterns including 3D palmprint and 3D fingerprint, to validate the effectiveness of the proposed approach.

Contactless personal identification using biometrics characteristics brings multifaceted advantages with improved hygiene, user security, and the convenience. Such imaging also generates deformation-free palmprint images which can lead to higher matching accuracy as the ground truth information is better preserved as compared with those from contact-based imaging. Advancement of palmprint identification technologies for new domains requires research using larger palmprint databases that are acquired from more realistic populations, under contactless, ambient, and indoor and outdoor environments. This paper presents such a new contactless palmprint database acquired from 600 different subjects, which is the largest to date and is also made available in the public domain. Unlike contactless fingerprints, contactless palmprint images often illustrate pose deformations along the optical axis of the camera, which also degrades the matching accuracy. This paper also introduces a new approach for matching contactless palmprint images using more accurate deformation alignment and matching. The experimental results are validated on three publicly available contactless palmprint databases. Comparative experimental results presented in this paper indicate consistently outperforming results over competing methods in the literature and validate the effectiveness of the investigated approach. These results also serve as baseline performance to advance much needed further research using the most challenging and largest database introduced from this paper.

Accurate comparison of contactless 2-D fingerprint images with contact-based fingerprints is critical for the success of emerging contactless 2-D fingerprint technologies, which offer more hygienic and deformation-free acquisition of fingerprint features. Convolutional neural networks (CNNs) have shown remarkable capabilities in biometrics recognition. However, there has been almost nil attempt to match fingerprint images using CNN-based approaches. This paper develops a CNN-based framework to accurately match contactless and contact-based fingerprint images. Our framework first trains a multi-Siamese CNN using fingerprint minutiae, respective ridge map and specific region of ridge map. This network is used to generate deep fingerprint representation using a distance-aware loss function. Deep fingerprint representations generated in such multi-Siamese network are concatenated for more accurate cross comparison. The proposed approach for cross-fingerprint comparison is evaluated on two publicly available databases containing contactless 2-D fingerprints and respective contact-based fingerprints. Our experiments presented in this paper consistently achieve outperforming results over several popular deep learning architectures and over contactless to contact-based fingerprints comparison methods in the literature.

Iris recognition has emerged as the more accurate, convenient, and low-cost biometric approach to authenticate human subjects. However, the accuracy offered by current popular iris recognition algorithms is below the expectations from the community, and therefore, researchers have recently focused their attention on deep learning-based methods. This paper investigates a new deep learning-based approach for iris recognition and attempts to improve the accuracy using a more simplified framework to more accurately recover the representative features. We consider residual network learning with dilated convolutional kernels to optimize the training process and aggregate contextual information from the iris images. Such an approach also alleviates the need for the down-sampling and up-sampling layers, which not only results in a simplified network but also results in outperforming matching accuracy over several classical and state-of-the-art algorithms for iris recognition, i.e., further improvement in equal error rates by 7.14%, 10.7%, and 27.4% on three test databases. In this paper, our reproducible experimental results are presented on three publicly available datasets that illustrate outperforming results and validate the usefulness of our approach.

Photometric stereo offers a single camera based approach to recover 3D information and has attracted wide range of applications in computer vision. Presence of non-Lambertian reflections in almost all the real-world objects limits the usage of the Lambertian model for surface normal vector estimation. Previous methods proposed to address such non-Lambertian phenomena employ an outlier rejection approach while more recent methods introduce BRDF models which can generate more accurate results. However, results with comparable accuracy can also be achieved by simply filtering the observed intensity values. This paper presents two novel outlier rejection techniques which attempt to identify the data which are more reliable and likely to be Lambertian. In the first technique, observed intensity values with less reliability are automatically eliminated. This reliability is determined by the responses from a newly introduced inter-relationship function. In the second technique, those photometric ratio equations which are less likely to be Lambertian are identified by observing the residue of the equations. By eliminating the data which is unreliable and likely to be non-Lambertian, surface normal vectors are more accurately estimated. Our comparative and reproducible experimental results using both real and synthetic datasets illustrate superior performance over the state-of-the-art methods, which validates our theoretical arguments presented in this paper.

The surface normal estimation from photometric stereo becomes less reliable when the surface reflectance deviates from the Lambertian assumption. The non-Lambertian effect can be explicitly addressed by physics modeling to the reflectance function, at the cost of introducing highly nonlinear optimization. This paper proposes a numerical compensation scheme that attempts to minimize the angular error to address the non-Lambertian photometric stereo problem. Due to the multifaceted influence in the modeling of non-Lambertian reflectance in photometric stereo, directly minimizing the angular errors of surface normal is a highly complex problem. We introduce an alternating strategy, in which the estimated reflectance can be temporarily regarded as a known variable, to simplify the formulation of angular error. To reduce the impact of inaccurately estimated reflectance in this simplification, we propose a numerical compensation scheme whose compensation weight is formulated to reflect the reliability of estimated reflectance. Finally, the solution for the proposed numerical compensation scheme is efficiently computed by using cosine difference to approximate the angular difference. The experimental results show that our method can significantly improve the performance of the state-of-the-art methods on both synthetic data and real data with small additive costs. Moreover, our method initialized by results from the baseline method (least-square-based) achieves the state-of-the-art performance on both synthetic data and real data with significantly smaller overall computation, i.e., about eight times faster compared with the state-of-the-art methods.

Accurate and efficient feature descriptors are crucial for the success of many pattern recognition tasks including human identification. Existing studies have shown that features extracted from 3D depth images are more reliable than those from 2D intensity images because intensity images are generally noisy and sensitive to illumination variation, which is challenging for many real-world applications like biometrics. Recently introduced 3D feature descriptors like Binary Shape and Surface Code have been shown improved effectiveness for 3D palm recognition. However, both methods lack theoretical support for the construction of the feature templates, which limits their matching accuracy and efficiency. In this paper, we further advance the Surface Code method and introduce the Efficient Surface Code, which describes whether a point tends to be concave or convex using only one bit per pixel. Our investigation also reveals that the discriminative abilities of the convex and concave regions are not necessarily equal. For example, line patterns on human palms and finger knuckles are expected to reveal more discriminative information than non-line regions. Therefore, we also propose a weighted similarity method in conjunction with the Efficient Surface Code instead of the traditional Hamming distance adopted in both Binary Shape and Surface Code. Comparative experimental results on both 3D palmprint and 3D finger knuckle databases illustrate superior performance to the aforementioned state-of-the-art methods, which validates our theoretical arguments.

Emerging 3D fingerprint recognition technologies have attracted growing attention in addressing the limitations from contact-based fingerprint acquisition and improve recognition accuracy. However, the complex 3D imaging setups employed in these systems typically require structured lighting with scanners or multiple cameras which are bulky with higher cost. This paper presents a more accurate and efficient 3D fingerprint identification approach using a single 2D camera with multiple colored LED illumination. A 3D minutiae tetrahedron based algorithm is developed to more efficiently match recovered minutiae features in 3D space and address the limitations of 3D minutiae matching approach in the literature. This algorithm significantly improves the matching time to about 15 times than the state-of-art in the reference. A hierarchical tetrahedron matching scheme is also developed to further improve the matching accuracy with faster speed. The 2D images acquired to reconstruct the 3D fingerprints are also used to recover 2D minutiae and further improve matching performance for 3D fingerprints. A new two-session database acquiring from 300 different clients consists of 2760 3D fingerprints reconstructed from 5520 colored 2D fingerprints is also developed and shared in public domain to further advance much needed research in this area. Extensive experimental results presented in this paper validate our approach and demonstrate the effectiveness of proposed algorithms.

Periocular recognition has been emerging as an effective biometric identification approach, especially under less constrained environments where face and/or iris recognition is not applicable. This paper proposes a new deep learning-based architecture for robust and more accurate periocular recognition which incorporates attention model to emphasize important regions in the periocular images. The new architecture adopts multi-glance mechanism, in which part of the intermediate components are configured to incorporate emphasis on important semantical regions, i.e., eyebrow and eye, within a periocular image. By focusing on these regions, the deep convolutional neural network is able to learn additional discriminative features, which in turn improves the recognition capability of the whole model. The superior performance of our method strongly suggests that eyebrow and eye regions are important for periocular recognition, and deserve special attention during the deep feature learning process. This paper also presents a customized verification-oriented loss function, which is shown to provide higher discriminating power than conventional contrastive/triplet loss functions. Extensive experiments on six publicly available databases are performed to evaluate the proposed approach. The reproducible experimental results indicate that our approach significantly outperforms several state-of-the-art methods for the periocular recognition.

Vast databases of billions of contact-based fingerprints have been developed to protect national borders and support e-governance programs. Emerging contactless fingerprint sensors offer better hygiene, security and accuracy. However the adoption/success of such contactless fingerprint technologies largely depends on advanced capability to match contactless 2D fingerprints with legacy contact-based fingerprint databases. This paper investigates such problem and develops a new approach to accurately match such fingerprint images. Robust thin-plate spline (RTPS) is developed to more accurately model elastic fingerprint deformations using splines. In order to correct such deformations on the contact-based fingerprints, RTPS based generalized fingerprint deformation correction model (DCM) is proposed. The usage of DCM results in accurate alignment of key minutiae features observed on the contactless and contactbased fingerprints. Further improvement in such cross-matching performance is investigated by incorporating minutiae related ridges. We also develop a new database of 1800 contactless 2D fingerprints and the corresponding contact-based fingerprints acquired from 300 clients which is made publicly accessible for further research. The experimental results presented in this paper, using two publicly available databases, validate our approach and achieve outperforming results for matching contactless 2D and contact-based fingerprint images.

Contactless 2D fingerprint identification is more hygienic, and enables deformation free imaging for higher accuracy. Success of such emerging contactless fingerprint technologies requires advanced capabilities to accurately match such fingerprint images with the conventional fingerprint databases which have been developed and deployed in last two decades. Convolutional neural networks have shown remarkable success for the face recognition problem. However, there has been very few attempts to develop CNN-based methods to address challenges in fingerprint identification problems. This paper proposes a multi-Siamese CNN architecture for accurately matching contactless and contact-based fingerprint images. In addition to the fingerprint images, hand-crafted fingerprint features, e.g. minutiae and core point, are also incorporated into the proposed architecture. This multi-Siamese CNN is trained using the fingerprint images and extracted features. Therefore, a more robust deep fingerprint representation is formed from the concatenation of deep feature vectors generated from multi-networks. In order to demonstrate the effectiveness of the proposed approach, a publicly available database consisting of contact-based and respective contactless finger-prints is utilized. The experimental evaluations presented in this paper achieve outperforming results, over other CNN-based methods and the traditional fingerprint cross matching methods, and validate our approach.

This paper proposes an accurate and generalizable deep learning framework for iris recognition. The proposed framework is based on a fully convolutional network (FCN), which generates spatially corresponding iris feature descriptors. A specially designed Extended Triplet Loss (ETL) function is introduced to incorporate the bit-shifting and non-iris masking, which are found necessary for learning discriminative spatial iris features. We also developed a sub-network to provide appropriate information for identifying meaningful iris regions, which serves as essential input for the newly developed ETL. Thorough experiments on four publicly available databases suggest that the proposed framework consistently outperforms several classic and state-of-the-art iris recognition approaches. More importantly, our model exhibits superior generalization capability as, unlike popular methods in the literature, it does not essentially require database-specific parameter tuning, which is another key advantage over other approaches.

Accurate biometric identification under real environments is one of the most critical and challenging tasks to meet growing demand for higher security. This paper proposes a new framework to efficiently and accurately match periocular images that are automatically acquired under less-constrained environments. Our framework, referred to as semantics-assisted convolutional neural networks (SCNNs) in this paper, incorporates explicit semantic information to automatically recover comprehensive periocular features. This strategy enables superior matching accuracy with the usage of relatively smaller number of training samples, which is often an issue with several biometrics. Our reproducible experimental results on four different publicly available databases suggest that the SCNN-based periocular recognition approach can achieve outperforming results, both in achievable accuracy and matching time, for less-constrained periocular matching. Additional experimental results presented in this paper also indicate that the effectiveness of proposed SCNN architecture is not only limited to periocular recognition but it can also be useful for generalized image classification. Without increasing the volume of training data, the SCNN is able to automatically extract more discriminative features from the input data than a single CNN, therefore can consistently improve the recognition performance. The experimental results presented in this paper validate such an approach to enable faster and more accurate periocular recognition under less constrained environments.

Iris recognition systems are increasingly deployed for large-scale applications such as national ID programs, which continue to acquire millions of iris images to establish identity among billions. However, with the availability of variety of iris sensors that are deployed for the iris imaging under different illumination/environment, significant performance degradation is expected while matching such iris images acquired under two different domains (either sensor-specific or wavelength-specific). This paper develops a domain adaptation framework to address this problem and introduces a new algorithm using Markov random fields model to significantly improve cross-domain iris recognition. The proposed domain adaptation framework based on the naive Bayes nearest neighbor classification uses a real-valued feature representation, which is capable of learning domain knowledge. Our approach to estimate corresponding visible iris patterns from the synthesis of iris patches in the near infrared iris images achieves outperforming results for the cross-spectral iris recognition. In this paper, a new class of bi-spectral iris recognition system that can simultaneously acquire visible and near infra-red images with pixel-to-pixel correspondences is proposed and evaluated. This paper presents experimental results from three publicly available databases; PolyU cross-spectral iris image database, IIITD CLI and UND database, and achieve outperforming results for the cross-sensor and cross-spectral iris matching.

Improving accuracy of matching fingerprint images acquired from two different fingerprint sensors is an important research problem with several promising studies in the literature. Most of these studies focus on sensor interoperability using fingerprints acquired from different kinds of contact-based sensors. However emerging contactless fingerprint technologies have shown its benefits. This paper investigates fingerprint sensor interoperability problem using fingerprints acquired from contact-based and contactless sensor. We propose a generalized contact-based fingerprint deformation correction model (DCM) to improve the matching accuracy. This model is trained by estimating the deformation between contact-based fingerprint and corresponding contactless fingerprint (ground truth). We present a method to estimate contact-based fingerprint impression type and intensity. As a result, minutiae features from contact-based and contactless fingerprint can be better aligned using the proposed model. A database of 1200 2D contactless fingerprints and respective contact-based fingerprints from 200 clients is used for the experiments. The experimental results presented in this paper validate our approach and illustrate promising improvement in performance using the proposed model.

Design and development of efficient and accurate feature descriptors is critical for the success of many computer vision applications. This paper proposes a new feature descriptor, referred to as DoN, for the 2D palmprint matching. The descriptor is extracted for each point on the palmprint. It is based on the ordinal measure which partially describes the difference of the neighboring points' normal vectors. DoN has at least two advantages: 1) it describes the 3D information, which is expected to be highly stable under commonly occurring illumination variations during contactless imaging; 2) the size of DoN for each point is only one bit, which is computationally simple to extract, easy to match, and efficient to storage. We show that such 3D information can be extracted from a single 2D palmprint image. The analysis for the effectiveness of ordinal measure for palmprint matching is also provided. Four publicly available 2D palmprint databases are used to evaluate the effectiveness of DoN, both for identification and the verification. Our method on all these databases achieves the state-of-the-art performance.

Finger or palm dorsal surface is inherently revealed while presenting (slap) fingerprints during border crossings or during day-to-day activities, such as driving, holding arms, signing documents, or playing sports. Finger knuckle patterns are believed to be correlated with the anatomy of fingers that involve complex interaction of finger bones, tissues, and skin, which can be uniquely identify the individuals. This paper investigates the possibility of using lowest finger knuckle patterns formed on joints between the metacarpal and proximal phalanx bones for the automated personal identification. We automatically segment such region of interest from the palm dorsal images and normalize/enhance them to accommodate illumination, scale, and pose variations resulting from the contactless imaging. The normalized knuckle images are investigated for the matching performance using several spatial and spectral domain approaches. We use database of 501 different subjects acquired from the contactless hand imaging to ascertain the performance. This paper also evaluates the possibility of using palm dorsal surface regions, in combination with minor knuckle patterns, and provides finger dorsal image database from 712 different subjects for the performance evaluation. The experimental results presented in this paper are very encouraging and demonstrates the potential of such unexplored minor finger knuckle patterns for the biometrics identification.

This paper introduces a generalized palmprint identification framework to unify several state-of-art 2D and 3D palmprint methods. Through this framework, we argue that the methods employing one-to-one matching strategy and binary representation for feature are more effective for palmprint identification. The analysis for the first argument is based on a statistical matching model and is supported by outperforming results on several publicly available 2D palmprpint databases. These two arguments are further evaluated for 3D palmprint matching and used to introduce a new method for encoding 3D palmprint feature. The proposed 3D feature is binary and more efficiently computed. It encodes the 3D shape of palmprint to either convex or concave. The experimental results on two publicly available, from contactless and contact-base 3D palmprint database of 177 and 200 subjects, respectively, outperform the state-of-the-art methods. This paper also provides our palmprint matching algorithm(s) in public domain, unlike the previous work in this area, which will help to further advance research efforts in this area.

This paper proposes a novel and more accurate iris segmentation framework to automatically segment iris region from the face images acquired with relaxed imaging under visible or near-infrared illumination, which provides strong feasibility for applications in surveillance, forensics and the search for missing children, etc. The proposed framework is built on a novel total-variation based formulation which uses l1 norm regularization to robustly suppress noisy texture pixels for the accurate iris localization. A series of novel and robust post processing operations are introduced to more accurately localize the limbic boundaries. Our experimental results on three publicly available databases, i.e., FRGC, UBIRIS.v2 and CASIA.v4-distance, achieve significant performance improvement in terms of iris segmentation accuracy over the state-of-the-art approaches in the literature. Besides, we have shown that using iris masks generated from the proposed approach helps to improve iris recognition performance as well. Unlike prior work, all the implementations in this paper are made publicly available to further advance research and applications in biometrics at-d-distance.

Human identification using fingerprint impressions has been widely studied and employed for more than 2000 years. Despite new advancements in the 3D imaging technologies, widely accepted representation of 3D fingerprint features and matching methodology is yet to emerge. This paper investigates 3D representation of widely employed 2D minutiae features by recovering and incorporating (i) minutiae height z and (ii) its 3D orientation φ information and illustrates an effective matching strategy for matching popular minutiae features extended in 3D space. One of the obstacles of the emerging 3D fingerprint identification systems to replace the conventional 2D fingerprint system lies in their bulk and high cost, which is mainly contributed from the usage of structured lighting system or multiple cameras. This paper attempts to addresses such key limitations of the current 3D fingerprint technologies bydeveloping the single camera-based 3D fingerprint identification system. We develop a generalized 3D minutiae matching model and recover extended 3D fingerprint features from the reconstructed 3D fingerprints. 2D fingerprint images acquired for the 3D fingerprint reconstruction can themselves be employed for the performance improvement and have been illustrated in the work detailed in this paper. This paper also attempts to answer one of the most fundamental questions on the availability of inherent discriminableinformation from 3D fingerprints. The experimental results are presented on a database of 240 clients 3D fingerprints, which is made publicly available to further research efforts in this area, and illustrate the discriminant power of 3D minutiae representation andmatching to achieve performance improvement.

In most human surveillance and forensic applications, key requirement is often to achieve highest possible true positive identification accuracy with a judicious compromise in accepting false positive identities. However with such scenario's in mind, there has been lack of any effort to develop adaptive security management for open set biometric recognition and most of the available prior work in literature has been focused on performance improvement for the rank-one recognition. This paper investigates the multimodal open set biometric recognition to address the conflicting requirements between the offered identification rate and high false positive identification rate while admitting possible unknown subjects/suspects in the higher rank (more than rank-one) list. The proposed approach attempts to offer accurate open set rank-K recognition which can automatically select a decision threshold to the desired/requested security level using ant colony optimization and provide a useful solution to a range of dynamic security problems in surveillance and high security applications. The performance evaluation of the proposed framework is ascertained through rigorous experimentation on three multimodal matchers from publicly available NIST BSSRlandXM2VTS databases.

Automated and accurate biometrics identification using periocular imaging has wide range of applications from human surveillance to improving performance for iris recognition systems, especially under less-constrained imaging environment. Restricted Boltzmann Machine is a generative stochastic neural network that can learn the probability distribution over its set of inputs. As a convolutional version of Restricted Boltzman Machines, CRBM aim to accommodate large image sizes and greatly reduce the computational burden. However in the best of our knowledge, the unsupervised feature learning methods have not been explored in biometrics area except for the face recognition. This paper explores the effectiveness of CRBM model for the periocular recognition. We perform experiments on periocular image database from the largest number of subjects (300 subjects as test subjects) and simultaneously exploit key point features for improving the matching accuracy. The experimental results are presented on publicly available database, the Ubripr database, and suggest effectiveness of RBM feature learning for automated periocular recognition with the large number of subjects. The results from the investigation in this paper also suggest that the supervised metric learning can be effectively used to achieve superior performance than the conventional Euclidean distance metric for the periocular identification.

Automated biometrics identification using finger knuckle images has increasingly generated interest among researchers with emerging applications in human forensics and biometrics. Prior efforts in the biometrics literature have only investigated the major finger knuckle patterns that are formed on the finger surface joining proximal phalanx and middle phalanx bones. This paper investigates the possible use of minor finger knuckle patterns, which are formed on the finger surface joining distal phalanx and middle phalanx bones. The minor finger knuckle patterns can either be used as independent biometric patterns or employed to improve the performance from the major finger knuckle patterns. A completely automated approach for the minor finger knuckle identification is developed with key steps for region of interest segmentation, image normalization, enhancement, and robust matching to accommodate image variations. This paper also introduces a new or first publicly available database for minor (also major) finger knuckle images from 503 different subjects. The efforts to develop an automated minor finger knuckle pattern matching scheme achieve promising results and illustrate its simultaneous use to significantly improve the performance over the conventional finger knuckle identification. Several open questions on the stability and uniqueness of finger knuckle patterns should be addressed before knuckle pattern/image evidence can be admissible as supportive evidence in a court of law. Therefore, this paper also presents a study on the stability of finger knuckle patterns from images acquired with an interval of 4–7 years. The experimental results and the images presented in this paper provide new insights on the finger knuckle pattern and identify the need for further work to exploit finger knuckle patterns in forensics and biometrics applications.

Accurate iris recognition from the distantly acquired face or eye images under less constrained environments require development of specialized strategies which can accommodate for significant image variations (e.g., scale, rotation, translation) and influence from multiple noise sources. A set of coordinate-pairs, which is referred to as geometric key in this paper is randomly generated and exclusively assigned to each subject enrolled into the system. Such geometric key uniquely defines the way how the iris features are encoded from the localized iris region pixels. Such iris encoding scheme involves computationally efficient and fast comparison operation on the locally assembled image patches using the locations defined by the geometric key. The image patches involved in such operation can be more tolerant to the noise. Scale and rotation changes in the localized iris region can be well accommodated by using the transformed geometric key. The binarized encoding of such local iris features still allows efficient computation of their similarity using Hamming distance. The superiority of the proposed iris encoding and matching strategy is ascertained by providing comparison with several state-of-the-art iris encoding and matching algorithms on three publicly available databases: UBIRIS.v2, FRGC, CASIA.v4-distance, which suggests the average improvements of 36.3%, 32.7%, and 29.6% in equal error rates, respectively, as compared with several competing approaches.

Accurate iris recognition from the distantly acquired face or eye images requires development of effective strategies which can account for significant variations in the segmented iris image quality. Such variations can be highly correlated with the consistency of encoded iris features and the knowledge that such fragile bits can be exploited to improve matching accuracy. A non-linear approach to simultaneously account for both local consistency of iris bit and also the overall quality of the weight map is proposed. Our approach therefore more effectively penalizes the fragile bits while simultaneously rewarding more consistent bits. In order to achieve more stable characterization of local iris features, a Zernike moment-based phase encoding of iris features is proposed. Such Zernike moments-based phase features are computed from the partially overlapping regions to more effectively accommodate local pixel region variations in the normalized iris images. A joint strategy is adopted to simultaneously extract and combine both the global and localized iris features. The superiority of the proposed iris matching strategy is ascertained by providing comparison with several state-of-the-art iris matching algorithms on three publicly available databases: UBIRIS.v2, FRGC, CASIA.v4-distance. Our experimental results suggest that proposed strategy can achieve significant improvement in iris matching accuracy over those competing approaches in the literature, i.e., average improvement of 54.3%, 32.7% and 42.6% in equal error rates, respectively for UBIRIS.v2, FRGC, CASIA.v4-distance.

Human identification using fingerprint impressions has been widely studied and employed for more than 2000 years. Despite new advancements in the 3D imaging technologies, widely accepted representation of 3D fingerprint features and matching methodology is yet to emerge. This paper investigates 3D representation of widely employed 2D minutiae features by recovering and incorporating (i) minutiae height z and (ii) its 3D orientation φ information and illustrates an effective matching strategy for matching popular minutiae features extended in 3D space. One of the obstacles of the emerging 3D fingerprint identification systems to replace the conventional 2D fingerprint system lies in their bulk and high cost, which is mainly contributed from the usage of structured lighting system or multiple cameras. This paper attempts to addresses such key limitations of the current 3D fingerprint technologies bydeveloping the single camera-based 3D fingerprint identification system. We develop a generalized 3D minutiae matching model and recover extended 3D fingerprint features from the reconstructed 3D fingerprints. 2D fingerprint images acquired for the 3D fingerprint reconstruction can themselves be employed for the performance improvement and have been illustrated in the work detailed in this paper. This paper also attempts to answer one of the most fundamental questions on the availability of inherent discriminable information from 3D fingerprints. The experimental results are presented on a database of 240 clients 3D fingerprints, which is made publicly available to further research efforts in this area, and illustrate the discriminant power of 3D minutiae representation and matching to achieve performance improvement.

Online iris recognition using distantly acquired images in a less imaging constrained environment requires the development of a efficient iris segmentation approach and recognition strategy that can exploit multiple features available for the potential identification. This paper presents an effective solution toward addressing such a problem. The developed iris segmentation approach exploits a random walker algorithm to efficiently estimate coarsely segmented iris images. These coarsely segmented iris images are postprocessed using a sequence of operations that can effectively improve the segmentation accuracy. The robustness of the proposed iris segmentation approach is ascertained by providing comparison with other state-of-the-art algorithms using publicly available UBIRIS.v2, FRGC, and CASIA.v4-distance databases. Our experimental results achieve improvement of 9.5%, 4.3%, and 25.7% in the average segmentation accuracy, respectively, for the UBIRIS.v2, FRGC, and CASIA.v4-distance databases, as compared with most competing approaches. We also exploit the simultaneously extracted periocular features to achieve significant performance improvement. The joint segmentation and combination strategy suggest promising results and achieve average improvement of 132.3%, 7.45%, and 17.5% in the recognition performance, respectively, from the UBIRIS.v2, FRGC, and CASIA.v4-distance databases, as compared with the related competing approaches.

This paper presents a new approach to improve the performance of finger-vein identification systems presented in the literature. The proposed system simultaneously acquires the finger-vein and low-resolution fingerprint images and combines these two evidences using a novel score-level combination strategy. We examine the previously proposed finger-vein identification approaches and develop a new approach that illustrates it superiority over prior published efforts. The utility of low-resolution fingerprint images acquired from a webcam is examined to ascertain the matching performance from such images. We develop and investigate two new score-level combinations, i.e., holistic and nonlinear fusion, and comparatively evaluate them with more popular score-level fusion approaches to ascertain their effectiveness in the proposed system. The rigorous experimental results presented on the database of 6264 images from 156 subjects illustrate significant improvement in the performance, i.e., both from the authentication and recognition experiments.

Remote human identification using iris biometrics has high civilian and surveillance applications and its success requires the development of robust segmentation algorithm to automatically extract the iris region. This paper presents a new iris segmentation framework which can robustly segment the iris images acquired using near infrared or visible illumination. The proposed approach exploits multiple higher order local pixel dependencies to robustly classify the eye region pixels into iris or noniris regions. Face and eye detection modules have been incorporated in the unified framework to automatically provide the localized eye region from facial image for iris segmentation. We develop robust postprocessing operations algorithm to effectively mitigate the noisy pixels caused by the misclassification. Experimental results presented in this paper suggest significant improvement in the average segmentation errors over the previously proposed approaches, i.e., 47.5%, 34.1%, and 32.6% on UBIRIS.v2, FRGC, and CASIA.v4 at-a-distance databases, respectively. The usefulness of the proposed approach is also ascertained from recognition experiments on three different publicly available databases.

This paper investigates new approaches for improving the conventional palmprint authentication performance by integrating color information. We firstly propose a new approach for image level combination of multiple color components to generate more reliable palmprint representation than the conventional gray level representation. This investigation is motivated to develop more robust palmprint representation that can be employed to achieve better performance for the conventional palmprint identification, with the same computational complexity. Secondly, this paper presents a rigorous analysis of different color representations for the palmprint images to ascertain the performance improvement using different feature representations (OLOF and SIFT) and different databases (scanner and webcam). The rigorous experimental results from this study suggest that the influence of color information can differently alter the performance gain, which varies with the nature of employed feature representation.

Two-dimensional (2-D) hand-geometry features carry limited discriminatory information and therefore yield moderate performance when utilized for personal identification. This paper investigates a new approach to achieve performance improvement by simultaneously acquiring and combining three-dimensional (3-D) and 2-D features from the human hand. The proposed approach utilizes a 3-D digitizer to simultaneously acquire intensity and range images of the presented hands of the users in a completely contact-free manner. Two new representations that effectively characterize the local finger surface features are extracted from the acquired range images and are matched using the proposed matching metrics. In addition, the characterization of 3-D palm surface using SurfaceCode is proposed for matching a pair of 3-D palms. The proposed approach is evaluated on a database of 177 users acquired in two sessions. The experimental results suggest that the proposed 3-D hand-geometry features have significant discriminatory information to reliably authenticate individuals. Our experimental results demonstrate that consolidating 3-D and 2-D hand-geometry features results in significantly improved performance that cannot be achieved with the traditional 2-D hand-geometry features alone. Furthermore, this paper also investigates the performance improvement that can be achieved by integrating five biometric features, i.e., 2-D palmprint, 3-D palmprint, finger texture, along with 3-D and 2-D hand-geometry features, that are simultaneously extracted from the user's hand presented for authentication.

This paper presents two new approaches to improve the performance of palm-vein-based identification systems presented in the literature. The proposed approach attempts to more effectively accommodate the potential deformations, rotational and translational changes by encoding the orientation preserving features and utilizing a novel region-based matching scheme. We systematically compare the previously proposed palm-vein identification approaches with our proposed ones on two different databases that are acquired with the contactless and touch-based imaging setup. We evaluate the performance improvement in both verification and recognition scenarios and analyze the influence of enrollment size on the performance. In this context, the proposed approaches are also compared for its superiority using single image enrollment on two different databases. The rigorous experimental results presented in this paper, on the databases of 100 and 250 subjects, consistently conforms the superiority of the proposed approach in both the verification and recognition scenario.

This paper presents a novel approach for hand matching that achieves significantly improved performance even in the presence of large hand pose variations. The proposed method utilizes a 3-D digitizer to simultaneously acquire intensity and range images of the user's hand presented to the system in an arbitrary pose. The approach involves determination of the orientation of the hand in 3-D space followed by pose normalization of the acquired 3-D and 2-D hand images. Multimodal (2-D as well as 3-D) palmprint and hand geometry features, which are simultaneously extracted from the user's pose normalized textured 3-D hand, are used for matching. Individual matching scores are then combined using a new dynamic fusion strategy. Our experimental results on the database of 114 subjects with significant pose variations yielded encouraging results. Consistent (across various hand features considered) performance improvement achieved with the pose correction demonstrates the usefulness of the proposed approach for hand based biometric systems with unconstrained and contact-free imaging. The experimental results also suggest that the dynamic fusion approach employed in this work helps to achieve performance improvement of 60% (in terms of EER) over the case when matching scores are combined using the weighted sum rule.

This paper investigates a new approach for the personal recognition using rank-level combination of multiple biometrics representations. There has been very little effort to study rank-level fusion approaches for multibiometrics combination and none using multiple palmprint representations. In this paper, we propose a new nonlinear rank-level fusion approach and present a comparative study of rank-level fusion approaches, which can be useful in combining multibiometrics fusion. The comparative experimental results from the publicly available multibiometrics scores and real hand biometrics data to evaluate/ascertain the rank-level combination using Borda count, logistic regression/weighted Borda count, highest rank method, and Bucklin method are presented. Our experimental results presented in this paper suggest that significant performance improvement in the recognition accuracy can be achieved as compared to those from individual palmprint representations. The rigorous experimental results presented in this paper also suggest that the proposed nonlinear rank-level approach outperforms the rank-level combination approaches presented in this paper.

This paper investigates a new approach for the personal recognition using rank level combination of multiple palmprint representations. There has been very little effort to study rank level fusion approaches for multi-biometrics combination and in particular for the palmprint identification. In this paper, we propose a new nonlinear rank level fusion approach and present a comparative study of rank level fusion approaches which can be useful in combining multi-biometrics fusion. The comparative experimental results from the real hand biometrics data to evaluate/ascertain the rank level combination using (i) Borda count, (ii) Logistic regression/Weighted Borda count, (iii) highest rank method and (iv) Bucklin Method are presented. Our experimental results presented in this paper suggest that significant performance improvement in the recognition accuracy can be achieved as compared to those from individual palmprint representations. The rigorous experimental results presented in this paper also suggest that the proposed nonlinear rank-level approach outperforms the existing approaches presented in the literature.

Personal identification using iris images has invited lots of attention in the literature and offered higher accuracy. However, the computational complexity in the feature extraction from the normalized iris images is still of key concern and further efforts are required to develop efficient feature extraction approaches. In this paper, we investigate a new approach for the efficient and effective extraction of iris features using localized Radon transforms. The feature extraction process exploits the orientation information from the local iris texture features using finite Radon transform. The dominant orientation from these Radon transform features is used to generate a binarized/compact feature representation. The similarity between two feature vectors is computed from the minimum matching distance that can account for the variations resulting from translation and rotation of the images. The feasibility of this approach is rigorously evaluated on two publically available iris image databases, i.e. IITD iris image database v1 and CASIA v3 iris image database. We also investigate the multi-scale analysis of iris images to enhance the performance. The experimental results presented in this paper are highly promising and suggest the computationally attractive alternative for the online iris identification.

This paper presents a new evolutionary approach for adaptive combination of multiple biometrics to ensure the optimal performance for the desired level of security. The adaptive combination of multiple biometrics is employed to determine the optimal fusion strategy and the corresponding fusion parameters. The score-level fusion rules are adapted to ensure the desired system performance using a hybrid particle swarm optimization model. The rigorous experimental results presented in this paper illustrate that the proposed score-level approach can achieve significantly better and stable performance over the decision-level approach. There has been very little effort in the literature to investigate the performance of an adaptive multimodal fusion algorithm on real biometric data. This paper also presents the performance of the proposed approach from the real biometric samples which further validate the contributions from this paper.

This paper investigates a new approach for personal authentication using fingerback surface imaging. The texture pattern produced by the finger knuckle bending is highly unique and makes the surface a distinctive biometric identifier. The finger geometry features can be simultaneously acquired from the same image at the same time and integrated to further improve the user-identification accuracy of such a system. The fingerback surface images from each user are normalized to minimize the scale, translation, and rotational variations in the knuckle images. This paper details the development of such an approach using peg-free imaging. The experimental results from the proposed approach are promising and confirm the usefulness of such an approach for personal authentication.

This paper presents a new approach to authenticate individuals using triangulation of hand vein images and simultaneous extraction of knuckle shape information. The proposed method is fully automated and employs palm dorsal hand vein images acquired from the low-cost, near infrared, contactless imaging. The knuckle tips are used as key points for the image normalization and extraction of region of interest. The matching scores are generated in two parallel stages: (i) hierarchical matching score from the four topologies of triangulation in the binarized vein structures and (ii) from the geometrical features consisting of knuckle point perimeter distances in the acquired images. The weighted score level combination from these two matching scores are used to authenticate the individuals. The achieved experimental results from the proposed system using contactless palm dorsal-hand vein images are promising (equal error rate of 1.14%) and suggest more user friendly alternative for user identification.

Personal authentication using hand images, especially with those acquired from the peg-free imaging, has very high user-acceptance and has invited lot of attention in the literature. This paper investigates a new approach to achieve the performance improvement by incorporating user quality into the matching stage. The proposed method of extracting user quality is based on the confidence of generating reliable matching scores from the user templates. The palmprint and hand-shape images are simultaneously extracted from the hand images and are used to ascertain the performance improvement for the individual trait. The experimental results presented in this paper show significant improvement in the performance while incorporating the proposed method of user quality in the matching stages. This user quality based fusion of two biometric modalities is also investigated and achieves significant improvement in the authentication performance.

This paper presents a new evolutionary approach for adaptive combination of multiple biometrics to dynamically ensure the performance for the desired level of security. The adaptive combination of multiple biometrics is achieved at the matching score level. The score level fusion rules are adapted to ensure the required/desired system performance using particle swarm optimization. The experimental results presented in this paper illustrates two main advantages of the proposed score-level approach over the decision level approach; better performance and stable performance that require smaller number of iterations. There has not been any effort in the literature to investigate the performance of adaptive multimodal fusion algorithm on real biometric data. This paper also presents the performance of the proposed algorithm on real biometric data which further validates contributions from this paper.

This paper details a fully automated face authentication system using low-cost near infrared imaging. The image normalization step consists of eye center localization, scale correction and orientation correction. This paper investigates the comparison and combination of four face matchers on the automatically normalized face images: elastic bunch graph matching (EBGM), trace transform, PCA, and LDA. The performance evaluation is presented on the near infrared images acquired from the 102 users in two sessions with different pose and expressions. Our experimental results achieve the best results with the EER of 3.92% from the EBGM matcher while the combination of results from the different matchers can significantly improve the performance and achieve the EER of 2.28 %. The near infrared face database developed in this work is also made publicly available to foster further research.

Tongue line refers to the surface of the tongue covered with fissures or lines in deep or shallow shape and is one type of important features in clinical practice of Traditional Chinese Tongue Diagnosis (TCTD). However, it is hard to extract tongue lines completely due to the large variation of the widths of tongue lines and the strong noise caused by the rough surface of tongue and uneven illumination. In this paper, an improved wide line detector (WLD) is presented for tongue line extraction. Based on the characteristics of tongue lines, the original WLD is improved to avoid the undesired separation of a wide line and the influence of uneven lighting conditions. The proposed method has been tested on a total of 286 tongue line images and our experimental results demonstrate that the improved WLD significantly outperforms the original WLD for tongue line extraction by improving the TPR 16.5%, FPR 44.6% and PM 33.4%, respectively.

We note that there are some discrepancies in the results reported in the previous titled paper. Our experiments indicate that the authors have considered only a subset of all possible fusion rules, contradicting the statement that all possible rules have been considered. Moreover, the authors state that only monotonic rules can be optimal, and therefore, all other rules can be ignored. However, our experimental results examining all possible rules demonstrate that a nonmonotonic rule can also be an optimum fusion rule.

This paper proposes a novel approach for rank level fusion which gives improved performance gain verified by experimental results. In the absence of ranked features and instead of using the entire template, we propose using K partitions of the template. The approach proposed in the paper is useful for generating sequential ranks and survivor lists on partitions of template to boost confidence levels by incorporating information from partitions. The proposed algorithm iteratively generates ranks for each partition of the user template. Ranks from template partitions are consolidated to estimate the fusion rank for the classification. This paper investigates rank level fusion for palmprint biometric using two approaches: (1) fixed threshold and resulting survivor list, and (2) iterative thresholds and iteratively refined survivor list. The above approaches achieve similar performances as related manifestations of fusion architecture. The experimental results support the proposition of high in-template similarity of palmprint for a user and its relevance to the intra-modal fusion framework. Experimental results using proposed approach on real palmprint data from 100 users show superior performance with recognition accuracy of 99 % as compared to recognition accuracy of 95% achieved with the conventional approach.

Iris is one of the most distinguishable features of a human body, which remains fairly stable throughout the lifetime of an individual. This makes iris recognition one of the most reliable methods for biometric based identification. This paper investigates a new technique to improve the performance of the system by using cohort information and user-quality as the weight in the matching. The proposed approach uses the cohort information at the decision stage as cascaded classifiers. However, the second stage is only used if the first stage classifier is uncertain of its decision. The experimental results from the decision-level classifiers combination are presented, which show that the cascaded classification system significantly outperforms the single classifier, especially at lower value of FAR which is most likely to be the operating point for any system. This paper also proposes a new approach to ascertain the user-quality (iris) and illustrates its usage in the performance improvement.

This paper investigates a new biometric system based on texture of the hand knuckles. The texture pattern produced by the finger knuckle bending is highly unique and makes the surface a distinctive biometric identifier. Hand geometry features can be acquired from the same image, at the same time and integrated to improve the performance of the system. The finger back surface images from each of the users are used to extract scale, translation and rotational invariant knuckle images. The proposed system, especially on the peg-free and non-contact imaging setup, achieves promising results when tested over a database of 105 users.

The biometrics based recognition systems proposed in the literature have not yet exploited user-specific dependencies in the feature level representation. This paper suggests and investigates the performance improvement of the existing biometric systems using the discretization of extracted features. The performance improvement due to the unsupervised and supervised discretization schemes is compared on verity of classifiers; KNN, naive Bayes, SVM and FFN. The experimental results on the hand-geometry database of 100 users achieve significant improvement in the recognition accuracy and confirm the usefulness of discretization in biometrics systems.

The hand-geometry-based recognition systems proposed in the literature have not yet exploited user-specific dependencies in the feature-level representation. We investigate the possibilities to improve the performance of the existing hand-geometry systems using the discretization of extracted features. This paper proposes employing discretization of hand-geometry features, using entropy-based heuristics, to achieve the performance improvement. The performance improvement due to the unsupervised and supervised discretization schemes is compared on a variety of classifiers: k-NN, naive Bayes, SVM, and FFN. Our experimental results on the database of 100 users achieve significant improvement in the recognition accuracy and confirm the usefulness of discretization in hand-geometry-based systems

This paper proposes a new bimodal biometric system using feature-level fusion of hand shape and palm texture. The proposed combination is of significance since both the palmprint and hand-shape images are proposed to be extracted from the single hand image acquired from a digital camera. Several new hand-shape features that can be used to represent the hand shape and improve the performance are investigated. The new approach for palmprint recognition using discrete cosine transform coefficients, which can be directly obtained from the camera hardware, is demonstrated. None of the prior work on hand-shape or palmprint recognition has given any attention on the critical issue of feature selection. Our experimental results demonstrate that while majority of palmprint or hand-shape features are useful in predicting the subjects identity, only a small subset of these features are necessary in practice for building an accurate model for identification. The comparison and combination of proposed features is evaluated on the diverse classification schemes; naive Bayes (normal, estimated, multinomial), decision trees (C4.5, LMT), k-NN, SVM, and FFN. Although more work remains to be done, our results to date indicate that the combination of selected hand-shape and palmprint features constitutes a promising addition to the biometrics-based personal recognition systems.

This paper investigates a new approach for the palmprint identification using real Gabor function (RGF) filtering. Inkless composite hand images have been used to automatically to extract the palmprints from peg-free imaging setup. These palmprints, after normalization, are subjected to selective feature sampling by a bank of RGF. Each of these filtered images has been used to extract significant features (PalmCode) from each of 6 concentric circular bands. Our preliminary experimental results using 400 low-resolution palmprint images achieve the recognition rate of 97.50% and also illustrate the shortcomings of results presented in earlier work. The results show the uniqueness of palmprint texture, even in the two hands of an individual and its possible use in biometrics based personal recognition.

This paper investigates the performance of a bimodal biometric system using fusion of shape and texture. We propose several new hand-shape features that can be used to represent the hand shape and improve the performance for hand-shape based user authentication. We also demonstrate the usefulness of discrete cosine transform (DCT) coefficients for palmprint authentication. The score level fusion of hand shape and palmprint features using product rule achieves best performance as compared to max or sum rule. The two hand shapes of an individual are anatomically similar. However, the palmprint information from the two hands can be combined to further improve performance and is investigated in this paper. Our experimental results on the database of 100 users achieve promising results and therefore confirms the usefulness of the proposed method.

A new method of surface inspection for textured materials is investigated. The linear FIR filters that offer optimal energy separation between the defect and defect-free regions of texture have been utilized. The performance of different feature separation criteria with reference to fabric defects has been evaluated. The issues relating to the design of optimal filters for supervised and unsupervised web inspection are discussed. A general web inspection system based on optimal filters is proposed. Experiments with this new approach have yielded excellent results. The on-line computational simplicity of using the proposed scheme confirms the usefulness of the approach for industrial inspection.

Investigates two methods for the detection of defects on textured surfaces using neural networks and support vector machines. Every pixel from the inspection image is characterized by a feature vector, which serves as a local measure of homogeneity of texture. The feature vectors from the gray-level arrangement of neighboring pixels are transformed to eigenspace using Principal Component Analysis (PCA). The transformed features from a predetermined set of training images are used to train the classifier. The trained classifier is used to classes every pixel from inspection image into two-class, i.e. with- or without-defect. The experimental results on real fabric defects show that the proposed scheme can successfully segment the defects from the inspection images.

The problem of automated defect detection in textured materials is investigated. A new approach for defect detection using linear FIR filters with optimized energy separation is proposed. The performance of different feature separation criteria with reference to fabric defects has been evaluated. The issues relating to the design of optimal filters for supervised and unsupervised web inspection are addressed. A general web inspection system based on the optimal filters is proposed. The experiments on this new approach have yielded excellent results. The low computational requirement confirms the usefulness of the approach for industrial inspection.