LivDet-Iris 2025 is the sixth edition of the iris liveness detection competition. Held every two to three years, the competition aims to foster the development of robust algorithms capable of detecting a wide range of physically-and digitally-presented attacks in iris biometrics. The 2025 edition obtained the largest number of submissions in the history of the competition: ten algorithms from five institutions, and one commercial iris recognition system. LivDet-Iris 2025 also introduced new tasks compared to previous editions: (Task 1) a benchmark offered by an industry partner, (Task 2) morphed iris images, in which two different-identity samples were blended into one image, and (Task 3) evaluation of presentation attack detection robustness against advanced manufacturing techniques for textured contact lenses. This edition, for the first time in the series, offers a systematic testing of a commercial iris recognition system (software and hardware) using physical artifacts presented to the sensor. Dermalog-Iris team submitted algorithms that won all tasks, achieving the area under the ROC curve of 90.57%, 68.23% and 99.99% in tasks 1, 2, and 3, respectively. Additionally, we include results for baseline algorithms, based on modern deep convolutional neural networks and trained with all available public datasets of iris images representing bona fide samples and anomalies (physical attacks, eye diseases, post-mortem cases, and synthetically-generated iris images). Test samples created for tasks 2 and 3, and baseline models are made available to offer the state-of-the-art benchmark for iris liveness detection.

Saliency-guided training, which directs model learning to important regions of images, has demonstrated generalization improvements across various biometric presentation attack detection (PAD) tasks. This paper presents its first application to fingerprint PAD. We conducted a 50-participant study to create a dataset of 800 human-annotated fingerprint perceptually-important maps, explored alongside algorithmically-generated "pseudosaliency," including minutiae-based, image quality-based, and autoencoder-based saliency maps. Evaluating on the 2021 Fingerprint Liveness Detection Competition testing set, we explore various configurations within five distinct training scenarios to assess the impact of saliency-guided training on accuracy and generalization. Our findings demonstrate the effectiveness of saliency-guided training for fingerprint PAD in both limited and large data contexts, and we present a configuration capable of earning the first place on the LivDet-2021 benchmark. Our results highlight saliency-guided training’s promise for increased model generalization capabilities, its effectiveness when data is limited, and its potential to scale to larger datasets in fingerprint PAD. All collected saliency data and trained models are released with the paper to support reproducible research.

Energy-Based Models (EBMs) modify dataset entropy to claim high calibration and adversarial robustness. Previously hindered in real-world tasks by a reliance on generative methods, a Non-Generative EBM (NGEBM) has been developed. However, it's accuracy in real-world tasks is unprovenThe use of Class Activation Maps (CAMs) to guide model attention in choosing features during training has seen increasing support. Within the task of synthetic face detection the Directed Region Of Interest Diminution (DROID) has used CAM entropy to achieve high accuracy, but it's calibration and adversarial robustness have not been demonstratedBoth utilize statistical methods to modify entropy at different levels, each offering distinct benefits. In this paper we introduce a multiple loss function component model, Regional and Energy-Based Integrated Salience (REBIS), with three loss function terms building on EBM and CAM entropy approaches. REBIS brings both calibration and adversarial robustness to synthetic face detection, maintaining its state-of-the-art accuracy.

Can we teach machines to assess the expertise of humans solving visual tasks automatically based on eye tracking features? This paper proposes AutoSIGHT, Automatic System for Immediate Grading of Human experTise, that classifies expert and non-expert performers, and builds upon an ensemble of features extracted from eye tracking data while the performers were solving a visual task. Results on the task of iris Presentation Attack Detection (PAD) used for this study show that with a small evaluation window of just 5 seconds, AutoSIGHT achieves an average average Area Under the ROC curve performance of 0.751 in subject-disjoint train-test regime, indicating that such detection is viable. Furthermore, when a larger evaluation window of up to 30 seconds is available, the Area Under the ROC curve (AUROC) increases to 0.8306, indicating the model is effectively leveraging more information at a cost of slightly delayed decisions. This work opens new areas of research on how to incorporate the automatic weighing of human and machine expertise into human-AI pairing setups, which need to react dynamically to nonstationary expertise distribution between the human and AI players (e.g., when the experts need to be replaced, or the task at hand changes rapidly). Along with this paper, we offer the eye tracking data used in this study collected from 6 experts and 53 non-experts solving iris PAD visual task.

Post-mortem iris recognition is an emerging application of iris-based human identification in a forensic setup. One factor that may be useful in conditioning iris recognition methods is the tissue decomposition level, which is correlated with the post-mortem interval (PMI), i.e. the number of hours that have elapsed since death. PMI, however, is not always available, and its precise estimation remains one of the core challenges in forensic examination. This paper presents the first known to us method of the PMI estimation directly from iris images captured after death. To assess the feasibility of the iris-based PMI estimation, we designed models predicting the PMI from (a) near-infrared (NIR), (b) visible (RGB), and (c) multispectral (RGB+NIR) forensic iris images. Models were evaluated following a 10-fold cross-validation, in (S1) sample-disjoint, (S2) subject-disjoint, and (S3) cross-dataset scenarios. We explore two data balancing techniques for S3: resampling-based balancing (S3-real), and synthetic data-supplemented balancing (S3 -synthetic), We found that using the multispectral data offers a spectacularly low mean absolute error (MAE) of≈ 3.5 hours in the scenario (S1), a bit worse MAE ≈ 17.5 hours in the scenario (S2), and MAE ≈ 45.77 hours in the scenario (S3). Additionally, supplementing the training set with synthetically-generated forensic iris images (S3-synthetic) significantly enhances the models' ability to generalize to new NIR, RGB and multispectral data collected in a different lab. This suggests that if the environmental conditions are favorable (e.g., bodies are kept in low temperatures), forensic iris images provide features that are in-dicative of the PMI and can be automatically estimated.

Leveraging human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the active research questions is where (in the model architecture or training pipeline) and how to efficiently incorporate always-limited human perceptual data into training strategies of models. In this paper, we introduce MENTOR (huMan pErceptioN-guided preTraining fOr increased geneRalization), which addresses this question through two unique rounds of training CNNs tasked with open-set anomaly detection. First, we train an autoencoder to learn human saliency maps given an input image, without any class labels. The autoencoder is thus tasked with discovering domain-specific salient features which mimic human perception. Second, we remove the decoder part, add a classification layer on top of the encoder, and train this new model conventionally, now using class labels. We show that MENTOR successfully raises the generalization performance across three different CNN backbones in a variety of anomaly detection tasks (demonstrated for detection of unknown iris presentation attacks, synthetically-generated faces, and anomalies in chest X-ray images) compared to traditional pretraining methods (e.g., sourcing the weights from ImageNet), and as well as state-of-the-art methods that incorporate human perception guidance into training. In addition, we demonstrate that MENTOR can be flexibly applied to existing human perception-guided methods and subsequently increasing their generalization with no architectural modifications.

Incorporating human-perceptual intelligence into model training has shown to increase the generalization capability of models in several difficult biometric tasks, such as presentation attack detection (PAD) and detection of synthetic samples. After the initial collection phase, human visual saliency (e.g., eye-tracking data, or handwritten annotations) can be integrated into model training through attention mechanisms, augmented training samples, or through human perception-related components of loss functions. Despite their successes, a vital, but seemingly neglected, aspect of any saliency-based training is the level of salience granularity (e.g., bounding boxes, single saliency maps, or saliency aggregated from multiple subjects) necessary to find a balance between reaping the full benefits of human saliency and the cost of its collection. In this paper, we explore several different levels of salience granularity and demonstrate that increased generalization capabilities of PAD and synthetic face detection can be achieved by using simple yet effective saliency post-processing techniques across several different CNNs.

This paper proposes a framework for a privacy-safe iris presentation attack detection (PAD) method, designed solely with synthetically-generated, identity-leakage-free iris images. Once trained, the method is evaluated in a classical way using state-of-the-art iris PAD benchmarks. We designed two generative models for the synthesis of ISO/IEC 19794-6-compliant iris images. The first model synthesizes bona fide-looking samples. To avoid "identity leakage," the generated samples that accidentally matched those used in the model’s training were excluded. The second model synthesizes images of irises with textured contact lenses and is conditioned by a given contact lens brand to have better control over textured contact lens appearance when forming the training set. Our experiments demonstrate that models trained solely on synthetic data achieve a lower but still reasonable performance when compared to solutions trained with iris images collected from human subjects. This is the first-of-its-kind attempt to use solely synthetic data to train a fully-functional iris PAD solution, and despite the performance gap between regular and the proposed methods, this study demonstrates that with the increasing fidelity of generative models, creating such privacy-safe iris PAD methods may be possible. The source codes and generative models trained for this work are offered along with the paper.

Face image synthesis has progressed beyond the point at which humans can effectively distinguish authentic faces from synthetically-generated ones. Recently developed synthetic face image detectors boast ``better-than-human'' discriminative ability, especially those guided by human perceptual intelligence during the model's training process. In this paper, we investigate whether these human-guided synthetic face detectors can assist non-expert human operators in the task of synthetic image detection when compared to models trained without human-guidance. We conducted a large-scale experiment with more than 1,560 subjects classifying whether an image shows an authentic or synthetically-generated face, and annotating regions supporting their decisions. In total, 56,015 annotations across 3,780 unique face images were collected. All subjects first examined samples without any AI support, followed by samples given (a) the AI's decision (``synthetic'' or ``authentic''), (b) class activation maps illustrating where the model deems salient for its decision, or (c) both the AI's decision and AI's saliency map. Synthetic faces were generated with six modern Generative Adversarial Networks. Interesting observations from this experiment include: (1) models trained with human-guidance, which are also more accurate in our experiments, offer better support to human examination of face images when compared to models trained traditionally using cross-entropy loss, (2) binary decisions presented to humans results in their better performance than when saliency maps are presented, (3) understanding the AI's accuracy helps humans to increase trust in a given model and thus increase their overall accuracy. This work demonstrates that although humans supported by machines achieve better-than-random accuracy of synthetic face detection, the approaches of supplying humans with AI support and of building trust are key factors determining high effectiveness of the human-AI tandem.

Subtle periodic signals such as blood volume pulse and respiration can be extracted from RGB video, enabling non-contact health monitoring at low cost. Advancements in remote pulse estimation - or remote photoplethysmography (rPPG) - are currently driven by deep learning solutions. However, modern approaches are trained and evaluated on benchmark datasets with ground truth from contact-P PG sensors. We present the first non-contrastive unsuper-vised learning framework for signal regression to mitigate the need for labelled video data. With minimal assumptions of periodicity and finite bandwidth, our approach discovers the blood volume pulse directly from unlabelled videos. We find that encouraging sparse power spectra within normal physiological bandlimits and variance over batches of power spectra is sufficient for learning visual features of periodic signals. We perform the first experiments utilizing unlabelled video data not specifically created for rPPG to train robust pulse rate estimators. Given the limited inductive biases and impressive empirical results, the approach is theoretically capable of discovering other periodic signals from video, enabling multiple physiological measurements without the need for ground truth signals.

This paper describes the results of the 2023 edition of the “LivDet” series of iris presentation attack detection (PAD) competitions. New elements in this fifth competition include (1) GAN-generated iris images as a category of presentation attack instruments (PAI), and (2) an evaluation of human accuracy at detecting PAI as a reference benchmark. Clarkson University and the University of Notre Dame contributed image datasets for the competition, composed of samples representing seven different PAI categories, as well as baseline PAD algorithms. Fraunhofer IGD, Beijing University of Civil Engineering and Architecture, and Hochschule Darmstadt contributed results for a total of eight PAD algorithms to the competition. Accuracy results are analyzed by different PAI types, and compared to human accuracy. Overall, the Fraunhofer IGD algorithm, using an attention-based pixel-wise binary supervision network, showed the best-weighted accuracy results (average classification error rate of 37.31%), while the Beijing University of Civil Engineering and Architecture’s algorithm won when equal weights for each PAI were given (average classification rate of 22.15%). These results suggest that iris PAD is still a challenging problem.

Energy-based models (EBM) have become increasingly popular within computer vision. EBMs bring a probabilistic approach to training deep neural networks (DNN) and have been shown to enhance performance in areas such as calibration, out-of-distribution detection, and adversarial resistance. However, these advantages come at the cost of estimating input data probabilities, usually using a Langevin based method such as Stochastic Gradient Langevin Dynamics (SGLD), which bring additional computational costs, require parameterization, caching methods for efficiency, and can run into stability and scaling issues. EBMs use dynamical methods to draw samples from the probability density function (PDF) defined by the current state of the network and compare them to the training data using a maximum log likelihood approach to learn the correct PDF. We propose a non-generative training approach, Non-Generative EBM (NG-EBM), that utilizes the Approximate Mass, identified by Grathwohl et al. [1], as a loss term to direct the training. We show that our NG-EBM training strategy retains many of the benefits of EBM in calibration, out-of-distribution detection, and adversarial resistance, but without the computational complexity and overhead of the traditional approaches. In particular, the NG-EBM approach improves the Expected Calibration Error by a factor of 2.5 for CIFAR10 and 7.5 times for CIFAR100, when compared to traditionally trained models.

Can deep learning models achieve greater generalization if their training is guided by reference to human perceptual abilities? And how can we implement this in a practical manner? This paper proposes a training strategy to ConveY Brain Oversight to Raise Generalization (CYBORG). This new approach incorporates human-annotated saliency maps into a loss function that guides the model’s learning to focus on image regions that humans deem salient for the task. The Class Activation Mapping (CAM) mechanism is used to probe the model’s current saliency in each training batch, juxtapose this model saliency with human saliency, and penalize large differences. Results on the task of synthetic face detection, selected to illustrate the effectiveness of the approach, show that CYBORG leads to significant improvement in accuracy on unseen samples consisting of face images generated from six Generative Adversarial Networks across multiple classification network architectures. We also show that scaling to even seven times the training data, or using non-human-saliency auxiliary information, such as segmentation masks, and standard loss cannot beat the performance of CYBORG-trained models. As a side effect of this work, we observe that the addition of explicit region annotation to the task of synthetic face detection increased human classification accuracy. This work opens a new area of research on how to incorporate human visual saliency into loss functions in practice. All data, code and trained models used in this work are offered with this paper.

Nonlinear iris texture deformations due to pupil size variations are one of the main factors responsible for within-class variance of genuine comparison scores in iris recognition. In dominant approaches to iris recognition, the size of a ring-shaped iris region is linearly scaled to a canonical rectangle, used further in encoding and matching. However, the biological complexity of the iris sphincter and dilator muscles causes the movements of iris features to be nonlinear in a function of pupil size, and not solely organized along radial paths. Alternatively to the existing theoretical models based on the biomechanics of iris musculature, in this paper we propose a novel deep autoencoder-based model that can effectively learn complex movements of iris texture features directly from the data. The proposed model takes two inputs, (a) an ISO-compliant near-infrared iris image with initial pupil size, and (b) the binary mask defining the target shape of the iris. The model makes all the necessary nonlinear deformations to the iris texture to match the shape of the iris in an image (a) with the shape provided by the target mask (b). The identity-preservation component of the loss function helps the model in finding deformations that preserve identity and not only the visual realism of the generated samples. We also demonstrate two immediate applications of this model: better compensation for iris texture deformations in iris recognition algorithms, compared to linear models, and the creation of a generative algorithm that can aid human forensic examiners, who may need to compare iris images with a large difference in pupil dilation. We offer the source codes and model weights available along with this paper.

Research in presentation attack detection (PAD) for iris recognition has largely moved beyond evaluation in “closed-set” scenarios, to emphasize ability to generalize to presentation attack types not present in the training data. This paper offers multiple contributions to understand and extend the state-of-the-art in open-set iris PAD. First, it describes the most authoritative evaluation to date of iris PAD. We have curated the largest publicly-available image dataset for this problem, drawing from 26 benchmarks previously released by various groups, and adding 150,000 images being released with this paper, to create a set of 450,000 images representing authentic iris and seven types of presentation attack instrument (PAI). We formulate a leave-one-PAI-out evaluation protocol, and show that even the best algorithms in the closed-set evaluations exhibit catastrophic failures on multiple attack types in the open-set scenario. This includes algorithms performing well in the most recent LivDet-Iris 2020 competition, which may come from the fact that the LivDet-Iris protocol emphasizes sequestered images rather than unseen attack types. Second, we evaluate the accuracy of five open-source iris presentation attack algorithms available today, one of which is newly-proposed in this paper, and build an ensemble method that beats the winner of the LivDet-Iris 2020 by a substantial margin. This paper demonstrates that closed-set iris PAD, when all PAIs are known during training, is a solved problem, with multiple algorithms showing very high accuracy, while open-set iris PAD, when evaluated correctly, is far from being solved. The newly-created dataset, new open-source algorithms, and evaluation protocol, all made publicly available with this paper, provide experimental artifacts that researchers can use to measure progress on this important problem.

Generative Adversarial Networks (GANs) have proven to be a preferred method of synthesizing fake images of ob-jects, such as faces, animals, and automobiles. It is not surprising these models can also generate ISO-compliant, yet synthetic iris images, which can be used to augment training data for iris matchers and liveness detectors. In this work, we trained one of the most recent GAN mod-els (StyleGAN3 [15]) to generate fake iris images with two primary goals: (i) to understand the GAN's ability to produce “never-before-seen” irises, and (ii) to investigate the phenomenon of identity leakage as a function of the GAN's training time. Previous work has shown that personal biometric data can inadvertently flow from training data into synthetic samples, raising a privacy concern for subjects who accidentally appear in the training dataset. This paper presents analysis for three different iris matchers at varying points in the GAN training process to diagnose where and when authentic training samples are in jeopardy of leaking through the generative process. Our results show that while most synthetic samples do not show signs of identity leak-age, a handful of generated samples match authentic (training) samples nearly perfectly, with consensus across all matchers. In order to prioritize privacy, security, and trust in the machine learning model development process, the re-search community must strike a delicate balance between the benefits of using synthetic data and the corresponding threats against privacy from potential identity leakage.

Deep learning has driven remarkable accuracy increases in many computer vision problems. One ongoing challenge is how to achieve the greatest accuracy in cases where training data is limited. A second ongoing challenge is that trained models oftentimes do not generalize well even to new data that is subjectively similar to the training set. We address these challenges in a novel way, with the first-ever (to our knowledge) exploration of encoding human judgement about salient regions of images into the training data. We compare the accuracy and generalization of a state-of-the-art deep learning algorithm for a difficult problem in biometric presentation attack detection when trained on (a) original images with typical data augmentations, and (b) the same original images transformed to encode human judgement about salient image regions. The latter approach results in models that achieve higher accuracy and better generalization, decreasing the error of the LivDet-Iris 2020 winner from 29.78% to 16.37%, and achieving impressive generalization in a leave-one-attack-type-out evaluation scenario. This work opens a new area of study for how to embed human intelligence into training strategies for deep learning to achieve high accuracy and generalization in cases of limited training data.

Remote photoplethysmography (rPPG) is a technique for estimating blood volume changes from reflected light without the need for a contact sensor. We present the first examples of presentation attacks in the digital and physical domains on rPPG from face video. Digital attacks are easily performed by adding imperceptible periodic noise to the input videos. Physical attacks are performed with illumination from visible spectrum LEDs placed in close proximity to the face, while still being difficult to perceive with the human eye. We also show that our attacks extend beyond medical applications, since the method can effectively generate a strong periodic pulse on 3D-printed face masks, which presents difficulties for pulse-based face presentation attack detection (PAD). The paper concludes with ideas for using this work to improve robustness of rPPG methods and pulse-based face PAD.

We present the Deception Detection and Physiological Monitoring (DDPM) dataset and initial baseline results on this dataset. Our application context is an interview scenario in which the interviewee attempts to deceive the interviewer on selected responses. The interviewee is recorded in RGB, near-infrared, and long-wave infrared, along with cardiac pulse, blood oxygenation, and audio. After collection, data were annotated for interviewer/interviewee, curated, ground-truthed, and organized into train / test parts for a set of canonical deception detection experiments. Baseline experiments found random accuracy for micro-expressions as an indicator of deception, but that saccades can give a statistically significant response. We also estimated subject heart rates from face videos (remotely) with a mean absolute error as low as 3.16 bpm. The database contains almost 13 hours of recordings of 70 subjects, and over 8 million visible-light, near-infrared, and thermal video frames, along with appropriate meta, audio and pulse oximeter data. To our knowledge, this is the only collection offering recordings of five modalities in an interview scenario that can be used in both deception detection and remote photoplethysmography research.

Generative adversarial networks (GANs) are able to generate high resolution photo-realistic images of objects that "do not exist." These synthetic images are rather difficult to detect as fake. However, the manner in which these generative models are trained hints at a potential for information leakage from the supplied training data, especially in the context of synthetic faces. This paper presents experiments suggesting that identity information in face images can flow from the training corpus into synthetic samples without any adversarial actions when building or using the existing model. This raises privacy-related questions, but also stimulates discussions of (a) the face manifold's characteristics in the feature space and (b) how to create generative models that do not inadvertently reveal identity information of real subjects whose images were used for training. We used five different face matchers (face_recognition, FaceNet, ArcFace, SphereFace and Neurotechnology MegaMatcher) and the StyleGAN2 synthesis model, and show that this identity leakage does exist for some, but not all methods. So, can we say that these synthetically generated faces truly do not exist? Databases of real and synthetically generated faces are made available with this paper to allow full replicability of the results discussed in this work.

Diversity and unpredictability of artifacts potentially presented to an iris sensor calls for presentation attack detection methods that are agnostic to specificity of presentation attack instruments. This article proposes a method that combines two-dimensional and three-dimensional properties of the observed iris to address the problem of spoof detection in case when some properties of artifacts are unknown. The 2D (textural) iris features are extracted by a state-of-the-art method employing Binary Statistical Image Features (BSIF) and an ensemble of classifiers is used to deliver 2D modality-related decision. The 3D (shape) iris features are reconstructed by a photometric stereo method from only two images captured under near-infrared illumination placed at two different angles, as in many current commercial iris recognition sensors. The map of normal vectors is used to assess the convexity of the observed iris surface. The combination of these two approaches has been applied to detect whether a subject is wearing a textured contact lens to disguise their identity. Extensive experiments with NDCLD'15 dataset, and a newly collected NDIris3D dataset show that the proposed method is highly robust under various open-set testing scenarios, and that it outperforms all available open-source iris PAD methods tested in identical scenarios. The source code and the newly prepared benchmark are made available along with this article.

Gabor kernels are widely accepted as dominant filters for iris recognition. In this work we investigate, given the current interest in neural networks, if Gabor kernels are the only family of functions performing best in iris recognition, or if better filters can be learned directly from iris data. We use (on purpose) a single-layer convolutional neural network as it mimics an iris code-based algorithm. We learn two sets of data-driven kernels; one starting from randomly initialized weights and the other from open-source set of Gabor kernels. Through experimentation, we show that the network does not converge on Gabor kernels, instead converging on a mix of edge detectors, blob detectors and simple waves. In our experiments carried out with three subject-disjoint datasets we found that the performance of these learned kernels is comparable to the open-source Gabor kernels. These lead us to two conclusions: (a) a family of functions offering optimal performance in iris recognition is wider than Gabor kernels, and (b) we probably hit the maximum performance for an iris coding algorithm that uses a single convolutional layer, yet with multiple filters. Released with this work is a framework to learn data-driven kernels that can be easily transplanted into open-source iris recognition software (for instance, OSIRIS - Open Source IRIS).

Launched in 2013, LivDet-Iris is an international competition series open to academia and industry with the aim to assess and report advances in iris Presentation Attack Detection (PAD). This paper presents results from the fourth competition of the series: LivDet-Iris 2020. This year's competition introduced several novel elements: (a) incorporated new types of attacks (samples displayed on a screen, cadaver eyes and prosthetic eyes), (b) initiated LivDet-Iris as an on-going effort, with a testing protocol available now to everyone via the Biometrics Evaluation and Testing (BEAT)* open-source platform to facilitate reproducibility and benchmarking of new algorithms continuously, and (c) performance comparison of the submitted entries with three baseline methods (offered by the University of Notre Dame and Michigan State University), and three open-source iris PAD methods available in the public domain. The best performing entry to the competition reported a weighted average APCER of 59.10% and a BPCER of 0.46% over all five attack types. This paper serves as the latest evaluation of iris PAD on a large spectrum of presentation attack instruments.

This paper proposes the first known to us open source hardware and software iris recognition system with presentation attack detection (PAD), which can be easily assembled for about 75 USD using Raspberry Pi board and a few peripherals. The primary goal of this work is to offer a low-cost baseline for spoof-resistant iris recognition, which may (a) stimulate research in iris PAD and allow for easy prototyping of secure iris recognition systems, (b) offer a low-cost secure iris recognition alternative to more sophisticated systems, and (c) serve as an educational platform. We propose a lightweight image complexity-guided convolutional network for fast and accurate iris segmentation, domain-specific human-inspired Binarized Statistical Image Features (BSIF) to build an iris template, and to combine 2D (iris texture) and 3D (photometric stereo-based) features for PAD. The proposed iris recognition runs in about 3.2 seconds and the proposed PAD runs in about 4.5 seconds on Raspberry Pi 3B+. The hardware specifications and all source codes of the entire pipeline are made available along with this paper.

This paper proposes an end-to-end iris recognition method designed specifically for post-mortem samples, and thus serving as a perfect application for iris biometrics in forensics. To our knowledge, it is the first method specific for verification of iris samples acquired after demise. We have fine-tuned a convolutional neural network-based segmentation model with a large set of diversified iris data (including post-mortem and diseased eyes), and combined Gabor kernels with newly designed, iris-specific kernels learnt by Siamese networks. The resulting method significantly outperforms the existing off-the-shelf iris recognition methods (both academic and commercial) on the newly collected database of post-mortem iris images and for all available time horizons since death. We make all models and the method itself available along with this paper.

This paper proposes the first known to us iris recognition methodology designed specifically for post-mortem samples. We propose to use deep learning-based iris segmentation models to extract highly irregular iris texture areas in post-mortem iris images. We show how to use segmentation masks predicted by neural networks in conventional, Gabor-based iris recognition method, which employs circular approximations of the pupillary and limbic iris boundaries. As a whole, this method allows for a significant improvement in post-mortem iris recognition accuracy over the methods designed only for ante-mortem irises, including the academic OSIRIS and commercial IriCore implementations. The proposed method reaches the EER less than 1% for samples collected up to 10 hours after death, when compared to 16.89% and 5.37% of EER observed for OSIRIS and IriCore, respectively. For samples collected up to 369 h post-mortem, the proposed method achieves the EER 21.45%, while 33.59% and 25.38% are observed for OSIRIS and IriCore, respectively. Additionally, the method is tested on a database of iris images collected from ophthalmology clinic patients, for which it also offers an advantage over the two other algorithms. This work is the first step towards post-mortem-specific iris recognition, which increases the chances of identification of deceased subjects in forensic investigations. The new database of post-mortem iris images acquired from 42 subjects, as well as the deep learning-based segmentation models are made available along with the paper, to ensure all the results presented in this manuscript are reproducible.

We propose a new iris presentation attack detection method using three-dimensional features of an observed iris region estimated by photometric stereo. Our implementation uses a pair of iris images acquired by a common commercial iris sensor (LG 4000). No hardware modifications of any kind are required. Our approach should be applicable to any iris sensor that can illuminate the eye from two different directions. Each iris image in the pair is captured under near-infrared illumination at a different angle relative to the eye. Photometric stereo is used to estimate surface normal vectors in the non-occluded portions of the iris region. The variability of the normal vectors is used as the presentation attack detection score. This score is larger for a texture that is irregularly opaque and printed on a convex contact lens, and is smaller for an authentic iris texture. Thus the problem is formulated as binary classification into (a) an eye wearing textured contact lens and (b) the texture of an actual iris surface (possibly seen through a clear contact lens). Experiments were carried out on a database of approx. 2,900 iris image pairs acquired from approx. 100 subjects. Our method was able to correctly classify over 95% of samples when tested on contact lens brands unseen in training, and over 98% of samples when the contact lens brand was seen during training. The source codes of the method are made available to other researchers.

Binarized statistical image features (BSIF) have been successfully used for texture analysis in many computer vision tasks, including iris recognition and biometric presentation attack detection. One important point is that all applications of BSIF in iris recognition have used the original BSIF filters, which were trained on image patches extracted from natural images. This paper tests the question of whether domain-specific BSIF can give better performance than the default BSIF. The second important point is in the selection of image patches to use in training for BSIF. Can image patches derived from eye-tracking experiments, in which humans perform an iris recognition task, give better performance than random patches? Our results say that (1) domain-specific BSIF features can out-perform the default BSIF features, and (2) selecting image patches in a task-specific manner guided by human performance can out-perform selecting random patches. These results are important because BSIF is often regarded as a generic texture tool that does not need any domain adaptation, and human-task-guided selection of patches for training has never (to our knowledge) been done. This paper follows the reproducible research requirements, and the new iris-domain-specific BSIF filters, the patches used in filter training, the database used in testing and the source codes of the designed iris recognition method are made available along with this paper to facilitate applications of this concept.

This paper advances the state of the art in human examination of iris images by (1) assessing the impact of different iris conditions in identity verification, and (2) introducing an annotation step that improves the accuracy of people's decisions. In a first experimental session, 114 subjects were asked to decide if pairs of iris images depict the same eye (genuine pairs) or two distinct eyes (impostor pairs). The image pairs sampled six conditions: (1) easy for algorithms to classify, (2) difficult for algorithms to classify, (3) large difference in pupil dilation, (4) disease-affected eyes, (5) identical twins, and (6) post-mortem samples. In a second session, 85 of the 114 subjects were asked to annotate matching and non-matching regions that supported their decisions. Subjects were allowed to change their initial classification as a result of the annotation process. Results suggest that: (a) people improve their identity verification accuracy when asked to annotate matching and non-matching regions between the pair of images, (b) images depicting the same eye with large difference in pupil dilation were the most challenging to subjects, but benefited well from the annotation-driven classification, (c) humans performed better than iris recognition algorithms when verifying genuine pairs of post-mortem and disease-affected eyes (i.e., samples showing deformations that go beyond the distortions of a healthy iris due to pupil dilation), and (d) annotation does not improve accuracy of analyzing images from identical twins, which remain confusing for people.

The adoption of large-scale iris recognition systems around the world has brought to light the importance of detecting presentation attack images (textured contact lenses and printouts). This paper presents a new approach in iris presentation attack detection (PAD) by exploring combinations of convolutional neural networks (CNNs) and transformed input spaces through binarized statistical image features (BSIFs). Our method combines lightweight CNNs to classify multiple BSIF views of the input image. Following explorations on complementary input spaces leading to more discriminative features to detect presentation attacks, we also propose an algorithm to select the best (and most discriminative) predictors for the task at hand. An ensemble of predictors makes use of their expected individual performances to aggregate their results into a final prediction. Results show that this technique improves on the current state of the art in iris PAD, outperforming the winner of LivDet-Iris 2017 competition both for intra- and cross-dataset scenarios, and illustrating the very difficult nature of the cross-dataset scenario.

This paper presents a comprehensive study of post-mortem human iris recognition carried out for 1200 near-infrared and 1787 visible-light samples collected from 37 deceased individuals kept in mortuary conditions. We used four independent iris recognition methods (three commercial and one academic) to analyze genuine and impostor comparison scores and check the dynamics of iris quality decay over a period of up to 814 h after death. This study shows that post-mortem iris recognition may be close-to-perfect approximately 5-7 h after death and occasionally is still viable even 21 days after death. These conclusions contradict the statements present in the past literature that the iris is unusable as a biometrics shortly after death, and show that the dynamics of post-mortem changes to the iris that are important for biometric identification are more moderate than previously hypothesized. This paper contains a thorough medical commentary that helps to understand which post-mortem metamorphoses of the eye may impact the performance of automatic iris recognition. An important finding is that false-match probability is higher when live iris images are compared with post-mortem samples than when only live samples are used in comparisons. This paper conforms to reproducible research and the database used in this study is made publicly available to facilitate research on post-mortem iris recognition. To the best of our knowledge, this paper offers the most comprehensive evaluation of post-mortem iris recognition and the largest database of post-mortem iris images.

Presentation attacks such as using a contact lens with a printed pattern or printouts of an iris can be utilized to bypass a biometric security system. The first international iris liveness competition was launched in 2013 in order to assess the performance of presentation attack detection (PAD) algorithms, with a second competition in 2015. This paper presents results of the third competition, LivDet-Iris 2017. Three software-based approaches to Presentation Attack Detection were submitted. Four datasets of live and spoof images were tested with an additional cross-sensor test. New datasets and novel situations of data have resulted in this competition being of a higher difficulty than previous competitions. Anonymous received the best results with a rate of rejected live samples of 3.36% and rate of accepted spoof samples of 14.71%. The results show that even with advances, printed iris attacks as well as patterned contacts lenses are still difficult for software-based systems to detect. Printed iris images were easier to be differentiated from live images in comparison to patterned contact lenses as was also seen in previous competitions.

This paper presents a solution to automatically recognize the correct left/right and upright/upside-down orientation of iris images. This solution can be used to counter spoofing attacks directed to generate fake identities by rotating an iris image or the iris sensor during the acquisition. Two approaches are compared on the same data, using the same evaluation protocol: 1) feature engineering, using hand-crafted features classified by a support vector machine (SVM) and 2) feature learning, using data-driven features learned and classified by a convolutional neural network (CNN). A data set of 20 750 iris images, acquired for 103 subjects using four sensors, was used for development. An additional subject-disjoint data set of 1,939 images, from 32 additional subjects, was used for testing purposes. Both same-sensor and cross-sensor tests were carried out to investigate how the classification approaches generalize to unknown hardware. The SVM-based approach achieved an average correct classification rate above 95% (89%) for recognition of left/right (upright/upside-down) orientation when tested on subject-disjoint data and camera-disjoint data, and 99% (97%) if the images were acquired by the same sensor. The CNN-based approach performed better for same-sensor experiments, and presented slightly worse generalization capabilities to unknown sensors when compared with the SVM. We are not aware of any other papers on the automatic recognition of upright/upside-down orientation of iris images, or studying both hand-crafted and data-driven features in same-sensor and cross-sensor subject-disjoint experiments. The data sets used in this paper, along with random splits of the data used in cross-validation, are being made available.

The primary objective of this paper is to propose a complete methodology for eye liveness detection based on pupil dynamics. This method may serve as a component of presentation attack detection in iris recognition systems, making them more secure. Due to a lack of public databases that would support this paper, we have built our own iris capture device to register pupil size changes under visible light stimuli, and registered 204 observations for 26 subjects (52 different irides), each containing 750 iris images taken every 40 ms. Each measurement registers the spontaneous pupil oscillations and its reaction after a sudden increase of the intensity of visible light. The Kohn and Clynes pupil dynamics model is used to describe these changes; hence we convert each observation into a feature space defined by model parameters. To answer the question whether the eye is alive (that is, if it reacts to light changes as a human eye) or the presentation is suspicious (that is, if it reacts oddly or no reaction is observed), we use linear and nonlinear support vector machines to classify natural reaction and spontaneous oscillations, simultaneously investigating the goodness of fit to reject bad modeling. Our experiments show that this approach can achieve a perfect performance for the data we have collected. All normal reactions are correctly differentiated from spontaneous oscillations. We investigated the shortest observation time required to model the pupil reaction, and found that time periods not exceeding 3 s are adequate to offer a perfect performance.

The use of an artificial replica of a biometric characteristic in an attempt to circumvent a system is an example of a biometric presentation attack. Liveness detection is one of the proposed countermeasures, and has been widely implemented in fingerprint and iris recognition systems in recent years to reduce the consequences of spoof attacks. The goal for the Liveness Detection (LivDet) competitions is to compare software-based iris liveness detection methodologies using a standardized testing protocol and large quantities of spoof and live images. Three submissions were received for the competition Part 1; Biometric Recognition Group de Universidad Autonoma de Madrid, University of Naples Federico II, and Faculdade de Engenharia de Universidade do Porto. The best results from across all three datasets was from Federico with a rate of falsely rejected live samples of 28.6% and the rate of falsely accepted fake samples of 5.7%.

We present here a report on a new Performance Evaluation System for Biometric Systems, which is secure, automatic and remote. This system will provide developers in Biometrics to progress in their works, avoiding problems with data protection policies related to testing, but without compromising the privacy of testing subjects. Biometric testing needs personal data to be recorded and used. Therefore in order to test their prototypes, researchers have to waste a lot of time and money for buying or creating testing databases. The solution described here offers the developers a secure and remote system which is available at all times, and which concentrates all private data in a secured centralized server. Also, as current standards, including standard APIs, are used, efforts needed by developers to use the system will be minimized, lowering also the overhead costs for testing purposes. The system is described by block diagrams as well as flowcharts.