Adam Czajka

Aliveness Detection for IRIS Biometrics

Various experiments show an alarming lack of anti-spoofing mechanisms in devices already protecting many sensitive areas all over the world, proving that aliveness detection methods must be quickly included in commercial equipment. To introduce and systemize the topic, the paper begins with a survey of possible types of eye forgery, together with possible countermeasures. The authors introduce three solutions of eye aliveness detection, based on analyses of image frequency spectrum, controlled light reflection from the cornea, and pupil dynamics. A body of various fake (printed) eye images was used to test the developed methodologies, including different printers and printout carriers. The proposed methodology was embedded into the NASK iris recognition system and showed its large potential. For a local database of pairs of alive and printed eyes, all methods proposed in the paper revealed zero false acceptance rate of fakes FAR-F. The false rejection rate of genuines FRR-G reached 2.8% for the first proposed solution, and showed null value for the next two proposed methods. This very favorable compares to the commercial equipment tested: two popular iris cameras accepted 73% and 15% of the prepared fake irises

Database of iris printouts and its application: Development of liveness detection method for iris recognition

Liveness detection (often referred to as presentation attack detection) is the ability to detect artificial objects presented to a biometric device with an intention to subvert the recognition system. This paper presents the database of iris printout images with a controlled quality, and its fundamental application, namely development of liveness detection method for iris recognition. The database gathers images of only those printouts that were accepted by an example commercial camera, i.e. the iris template calculated for an artefact was matched to the corresponding iris reference of the living eye. This means that the quality of the employed imitations is not accidental and precisely controlled. The database consists of 729 printout images for 243 different eyes, and 1274 images of the authentic eyes, corresponding to imitations. It may thus serve as a good benchmark for at least two challenges: a) assessment of the liveness detection algorithms, and b) assessment of the eagerness of matching real and fake samples by iris recognition methods. To our best knowledge, the iris printout database of such properties is the first worldwide published as of today. In its second part, the paper presents an example application of this database, i.e. the development of liveness detection method based on iris image frequency analysis. We discuss how to select frequency windows and regions of interest to make the method sensitive to “alien frequencies” resulting from the printing process. The proposed method shows a very promising results, since it may be configured to achieve no false alarms when the rate of accepting the iris printouts is approximately 5% (i.e. 95% of presentation attack trials are correctly identified). This favorable compares to the results of commercial equipment used in the database development, as this device accepted all the printouts used. The method employs the same image as used in iris recognition process, hence no investments into the capture devices is required, and may be applied also to other carriers for printed iris patterns, e.g. contact lens.

LivDet-iris 2013 - Iris Liveness Detection Competition 2013

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%.

IRIS Biometrics for Secure Remote Access

We propose a new iris texture coding technique with optimal feature extraction, and design a secure remote (internet) access system using the proposed biometrics. The proposed iris coding method is based on Zak-Gabor coefficients sequence, and additionally uses an optimal selection of a subset of iris features. The secure access involves a communication scenario that employs a usual client-server network model, thus incorporating standard security mechanisms with biometric enhancements. The proposed access scenario enables to include the aliveness detection capability and the biometric replay attack prevention.

Influence of Iris Template Aging on Recognition Reliability

The paper presents an iris aging analysis based on comparison results obtained for four different iris matchers. We collected an iris aging database of samples captured even eight years apart. To our best knowledge, this is the only database worldwide of iris images collected with such a large time distance between capture sessions. We evaluated the influence of the intra- vs. inter-session accuracy of the iris recognition, as well as the accuracy between the short term (up to two years) vs. long term comparisons (from 5 to 9 years). The average genuine scores revealed statistically significant differences with respect to the time distance between examined samples (up to 14 % of degradation in the average genuine scores is observed). These results may suggest that the iris pattern ages to some extent, and thus appropriate countermeasures should be deployed in application assuming large time distances between iris template replacements (or adaptations).

Cataract influence on iris recognition performance

This paper presents the experimental study revealing weaker performance of the automatic iris recognition methods for cataract-affected eyes when compared to healthy eyes. There is little research on the topic, mostly incorporating scarce databases that are often deficient in images representing more than one illness. We built our own database, acquiring 1288 eye images of 37 patients of the Medical University of Warsaw. Those images represent several common ocular diseases, such as cataract, along with less ordinary conditions, such as iris pattern alterations derived from illness or eye trauma. Images were captured in near-infrared light (used in biometrics) and for selected cases also in visible light (used in ophthalmological diagnosis). Since cataract is a disorder that is most populated by samples in the database, in this paper we focus solely on this illness. To assess the extent of the performance deterioration we use three iris recognition methodologies (commercial and academic solutions) to calculate genuine match scores for healthy eyes and those influenced by cataract. Results show a significant degradation in iris recognition reliability manifesting by worsening the genuine scores in all three matchers used in this study (12% of genuine score increase for an academic matcher, up to 175% of genuine score increase obtained for an example commercial matcher). This increase in genuine scores affected the final false non-match rate in two matchers. To our best knowledge this is the only study of such kind that employs more than one iris matcher, and analyzes the iris image segmentation as a potential source of decreased reliability

Recognition of Image-Orientation-Based Iris Spoofing

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.

Human iris recognition in post-mortem subjects: Study and database

This paper presents a unique study of post-mortem human iris recognition and the first known to us database of near-infrared and visible-light iris images of deceased humans collected up to almost 17 days after death. We used four different iris recognition methods to analyze the dynamics of iris quality decay in short-term comparisons (samples collected up to 60 hours after death) and long-term comparisons (for samples acquired up to 407 hours after demise). This study shows that post-mortem iris recognition is possible and occasionally works even 17 days after death. These conclusions contradict a promulgated rumor that iris is unusable shortly after decease. We make this dataset publicly available to let others verify our findings and to research new aspects of this important and unfamiliar topic. We are not aware of any earlier papers offering post-mortem human iris images and such comprehensive analysis employing four different matchers.

Assessment of iris recognition reliability for eyes affected by ocular pathologies

This paper presents an analysis of how the iris recognition is impacted by eye diseases and an appropriate dataset comprising 2996 iris images of 230 distinct eyes (including 184 illness-affected eyes representing more than 20 different eye conditions). The images were collected in near infrared and visible light during a routine ophthalmological practice. The experimental study shows four valuable results. First, the enrollment process is highly sensitive to those eye conditions that make the iris obstructed or introduce geometrical distortions. Second, even those conditions that do not produce visible changes to the iris structure may increase the dissimilarity among samples of the same eyes. Third, eye conditions affecting iris geometry, its tissue structure or producing obstructions significantly decrease the iris recognition reliability. Fourth, for eyes afflicted by a disease, the most prominent effect of the disease on iris recognition is to cause segmentation errors. To our knowledge this is the first database of iris images for disease-affected eyes made publicly available to researchers, and the most comprehensive study of what we can expect when the iris recognition is deployed for non-healthy eyes.

Biometric verification based on hand thermal images

The paper presents a biometric recognition methodology based on hand thermal information. We start with a hardware presentation, specially designed for this research in a form of thermal sensor plate delivering hand thermal maps, which is a significantly cheaper alternative to thermal cameras. We use a heuristic feature selection technique employing mutual information (mRMR) and well known space transformation methods (PCA and its combination with the LDA) to develop optimal biometric features by selecting those parts of the hand, which deliver the most discriminating personal information. Two different classifiers (k-NN and SVM) are applied and evaluated with a database of hand thermal maps captured for 50 different individuals in three sessions: two at the same day (enrollment attempts), and the third captured a week apart (verification attempt). We achieved 6.67% of an average equal error rate (EER), what suggests that temperature distribution of an inner part of human hand is individual. This may serve as e.g. supporting modality of two-modal biometric recognition (merged with hand geometry or palm print techniques), or may be a good candidate for hand liveness detection approach, as hand thermal maps are difficult to be copied and reconstructed on an artificial object imitating a human hand. To our best knowledge, this is the first work presenting the use of a human hand thermal maps as a direct source of biometric features.