Pupil Light Reflex Mitigation Using Non-linear Image Warping

Traditional biometric systems are designed and configured to operate in predefined circumstances to address the needs of a particular application. The performance of such biometrics systems tend to decrease because when they encounter varying conditions as they are unable to adapt to such variations. Many real-life scenarios require identification systems to recognise uncooperative people in uncontrolled environments. Therefore, there is a real need to design biometric systems that are aware of their context and be able to adapt to changing conditions. The context-awareness and adaptation of a biometric system are based on a set of factors that include: the application (e.g. healthcare system, border control, unlock smart devices), environment (e.g. quiet/noisy, indoor/outdoor), desired and pre-defined requirements (e.g. speed, usability, reliability, accuracy, robustness to high/low quality samples), user of the system (e.g. cooperative or non-cooperative), the chosen modality (e.g. face, speech, gesture signature), and used techniques (e.g. pre-processing to normalise and clean biometrics data, feature extraction and classification). These factors are linked and might affect each other, hence the system has to work adaptively to meet its overall aim based to its operational context. The aim of this research is to develop a multiagent based framework to represent a context-aware adaptive biometric system. This is to improve the decision making process at each processing step of traditional biometric identification systems. Agents will be used to provide the system with intelligence, adaptation, flexibility, automation, and reliability during the identification process. The framework will accommodate at least five agents, one for each of the five main processing steps of a typical biometric system (i.e. data capture, pre-processing, feature extraction, classification and decision). Each agent can contribute differently towards its designated goal to achieve the best possible solution by selecting/ applying the best technique. For example, an agent can be used to assess the quality of the input biometric sample to ensure the important features can be extracted and processed in further steps. Another agent can be used to pre-process the biometric sample if necessary. A third agent is used to select the appropriate set of features followed by another to select a suitable classifier that works well in a given condition.

The 2018 Biometric Technology Rally was an evaluation, sponsored by the U.S. Department of Homeland Security, Science and Technology Directorate (DHS S&T), that challenged industry to provide face or face/iris systems capable of unmanned, traveler identification in a high-throughput security environment. Selected systems were installed at the Maryland Test Facility (MdTF), a DHS S&T affiliated bio-metrics testing laboratory, and evaluated using a population of 363 naive human subjects recruited from the general public. The performance of each system was examined based on measured throughput, capture capability, matching capability, and user satisfaction metrics. This research documents the performance of unmanned face and face/iris systems required to maintain an average total subject interaction time of less than 10 seconds. The results highlight discrepancies between the performance of biometric systems as anticipated by the system designers and the measured performance, indicating an incomplete understanding of the main determinants of system performance. Our research shows that failure-to-acquire errors, unpredicted by system designers, were the main driver of non-identification rates instead of failure-to-match errors, which were better predicted. This outcome indicates the need for a renewed focus on reducing the failure-to-acquire rate in high-throughput, unmanned biometric systems.

Score normalization applied to adaptive biometric systems

The use of biometric systems in physical access scenarios is gaining popularity. In such scenarios, users are enroled under well controlled conditions and the enrolment is usually indoors. To gain access to the building, the user provides his biometric samples in an outdoor environment over which there is little control. This adversely affects the quality of the samples and as a result the system performance is sub-optimal. This study evaluates the performance of a multimodal biometric system in a physical access scenario. We evaluate leading commercial algorithms on an indoor-outdoor, multimodal database comprising of face and voice samples. The indoor-outdoor nature of the database and the choice of modalities results in individual systems performing poorly. Popular normalization and fusion techniques are used to improve the performance of the overall system. Multimodal fusion results in an average improvement of approximately 20% at 1% false acceptance rate over individual modalities.

Today, the use of iris recognition is expanding globally as the most accurate and reliable biometric feature in terms of uniqueness and robustness. The motivation for the reduction or compression of the large databases of iris images becomes an urgent requirement. In general, image compression is the process to remove the insignificant or redundant information from the image details, that implicitly makes efficient use of redundancy embedded within the image itself. In addition, it may exploit human vision or perception limitations to reduce the imperceptible information. This paper deals with reducing the size of image, namely reducing the number of bits required in representing the image. This was performed by exploiting the transforms-based coding techniques of lossless base compression system. In these techniques, the first part looked at the traditional Fourier transform coding technique while the second part aimed at enhancing the performance of the traditional transformation techniques. This was achieved once by overcoming the inherited problems of this technique that suffers from the complex nature base, then latter by incorporating the double base coding techniques of hierarchal scheme, as mixing of both discrete wavelet transform and zipper coding techniques.
 The test results indicated that the proposed scheme produced high compression ratio with identically preserving the quality of the compressed (decoded) image.

A facial morph is a synthetically created image of a face that looks similar to two different individuals and can even trick biometric facial recognition systems into recognizing both individuals. This attack is known as face morphing attack. The process of creating such a facial morph is well documented and a lot of tutorials and software to create them are freely available. Therefore, it is mandatory to be able to detect this kind of fraud to ensure the integrity of the face as reliable biometric feature. In this work, we study the effects of face morphing on the physically correctness of the illumination. We estimate the direction to the light sources based on specular highlights in the eyes and use them to generate a synthetic map for highlights on the skin. This map is compared with the highlights in the image that is suspected to be a fraud. Morphing faces with different geometries, a bad alignment of the source images or using images with different illuminations, can lead to inconsistencies in reflections that indicate the existence of a morphing attack.

The human iris is traditionally imaged in Near Infrared (NIR) wavelengths (700nm-900nm) for iris recognition. The absorption co-efficient of color inducing pigment in iris, called Melanin, decreases after 700nm thus minimizing its effect when iris is imaged at wavelengths greater than 700nm. This thesis provides an overview and explores the efficacy of iris recognition at different wavelength bands ranging from visible spectrum (450nm-700nm) to NIR (700nm-900nm) and Short Wave Infrared (900nm-1600nm). Different matching methods are investigated at different wavelength bands to facilitate cross-spectral iris recognition.;The iris recognition analysis in visible wavelengths provides a baseline performance when iris is captured using common digital cameras. A novel blob-based matching algorithm is proposed to match RGB (visible spectrum) iris images. This technique generates a match score based on the similarity between blob like structures in the iris images. The matching performance of the blob based matching method is compared against that of classical 'Iris Code' matching method, SIFT-based matching method and simple correlation matching, and results indicate that the blob-based matching method performs reasonably well. Additional experiments on the datasets show that the iris images can be matched with higher confidence for light colored irides than dark colored irides in the visible spectrum.;As part of the analysis in the NIR spectrum, iris images captured in visible spectrum are matched against those captured in the NIR spectrum. Experimental results on the WVU multispectral dataset show promise in achieving a good recognition performance when the images are captured using the same sensor under the same illumination conditions and at the same resolution. A new proprietary 'FaceIris' dataset is used to investigate the ability to match iris images from a high resolution face image in visible spectrum against an iris image acquired in NIR spectrum. Matching in 'FaceIris' dataset presents a scenario where the two images to be matched are obtained by different sensors at different wavelengths, at different ambient illumination and at different resolution. Cross-spectral matching on the 'FaceIris' dataset presented a challenge to achieve good performance. Also, the effect of the choice of the radial and angular parameters of the normalized iris image on matching performance is presented. The experiments on WVU multispectral dataset resulted in good separation between genuine and impostor score distributions for cross-spectral matching which indicates that iris images in obtained in visible spectrum can be successfully matched against NIR iris images using 'IrisCode' method.;Iris is also analyzed in the Short

This research discusses the evaluation of biometric systems that are designed to process hundreds to tens of thousands of individuals in short time spans. We propose a method for evaluating a system's performance across capture attempts for the purpose of identifying characteristics that are advantageous in these high-throughput environments. We also present a novel modification to the traditionally accepted biometric performance metrics of failure-to-acquire, and true-match rate. Namely, this paradigm shift holds that these metrics are a function of time and, as such, vary with the time available for a biometric system to interact with a user. This research demonstrates the utility of these time-based metrics in evaluating the performance of multiple, commercially available, high-throughput systems. We show that different biometric systems have notably different time-based performance curves using a corpus of data collected during the 2018 Department of Homeland Security, Science and Technology Directorate (DHS S&T) Biometric Technology Rally. These curves and the deviations between them are useful when quantifying the suitability of a technology, evaluated via scenario testing, for deployment in an operational environment where the throughput of the target population is a key performance parameter.

With the use of computers and Internet in every major activity of our society, security is increasingly important. Biometric recognition is not only challenging but also computationally demanding. This chapter aims develop an iris biometric system. The iris has the advantages of uniqueness, stableness, anti-spoof, non-invasiveness and efficiency and could be applied in almost every area (banking, forensics, access control, etc.). The performance of a biometric classification system is largely depending on the techniques used for feature extraction. Inspired by the biological plausibility of ordinal measures, we propose their employment for iris representation and recognition. Qualitative measurement, associated to the relative ordering of different characteristics, is defined as ordinal measurement. Besides the proposing of a novel, fast and robust, ordinal based feature extraction method, the chapter also considers the problem of designing the decision making model so as to obtain an efficient and effective biometric system. In the literature, there are different approaches for iris recognition, nevertheless, there are still challenging open problems in improving the accuracy, robustness, security and ergonomics of biometric systems.

Although iris recognition technology has been reported to be more stable and reliable than other biometric systems, performance can be degraded due to many factors such as small eyes, camera defocusing, eyelash occlusions and specular reflections on the surface of glasses. In this paper, we propose a new multi-unit iris authentication method that uses score level fusion based on a support vector machine (SVM) and a quality assessment method for mobile phones. Compared to previous research, this paper presents the following two contributions. First, we reduced the false rejection rate and improved iris recognition accuracy by using iris quality assessment. Second, if even two iris images were determined to be of bad quality, we captured the iris images again without using a recognition process. If only one iris image among the left and right irises was regarded as a good one, it was used for recognition. However, if both the left and right iris images were good, we performed multi-unit iris recognition using score level fusion based on a SVM. Experimental results showed that the accuracy of the proposed method was superior to previous methods that used only one good iris image or those methods that used conventional fusion methods.

Human iris is considered a reliable and accurate modality for biometric recognition due to its unique texture information. However, similar to other biometric modalities, iris recognition systems are also vulnerable to presentation attacks (commonly called spoofing) that attempt to conceal or impersonate identity. Examples of typical iris spoofing attacks are printed iris images, textured contact lenses, and synthetic creation of iris images. It is critical to note that majority of the algorithms proposed in the literature are trained to handle a specific type of spoofing attack. These algorithms usually perform very well on that particular attack. However, in real-world applications, an attacker may perform different spoofing attacks. In such a case, the problem becomes more challenging due to inherent variations in different attacks. In this paper, we focus on a medley of iris spoofing attacks and present a unified framework for detecting such attacks. We propose a novel structural and textural feature based iris spoofing detection framework (DESIST). Multi-order dense Zernike moments are calculated across the iris image which encode variations in structure of the iris image. Local Binary Pattern with Variance (LBPV) is utilized for representing textural changes in a spoofed iris image. The highest classification accuracy of 82.20% is observed by the proposed framework for detecting normal and spoofed iris images on a combined iris spoofing database.

The most established technique for the identification at biometric access control systems is the human fingerprint. While every human fingerprint is unique, fingerprints can be faked very easily by using thin layer fakes. Because commercial fingerprint scanners use only a two-dimensional image acquisition of the finger surface, they can only hardly differentiate between real fingerprints and fingerprint fakes applied on thin layer materials. A Swept Source OCT system with an A-line rate of 20 kHz and a lateral and axial resolution of approximately 13 μm, a centre wavelength of 1320 nm and a band width of 120 nm (FWHM) was used to acquire fingerprints and finger tips with overlying fakes. Three-dimensional volume stacks with dimensions of 4.5 mm x 4 mm x 2 mm were acquired. The layering arrangement of the imaged finger tips and faked finger tips was analyzed and subsequently classified into real and faked fingerprints. Additionally, sweat gland ducts were detected and consulted for the classification. The manual classification between real fingerprints and faked fingerprints results in almost 100 % correctness. The outer as well as the internal fingerprint can be recognized in all real human fingers, whereby this was not possible in the image stacks of the faked fingerprints. Furthermore, in all image stacks of real human fingers the sweat gland ducts were detected. The number of sweat gland ducts differs between the test persons. The typical helix shape of the ducts was observed. In contrast, in images of faked fingerprints we observe abnormal layer arrangements and no sweat gland ducts connecting the papillae of the outer fingerprint and the internal fingerprint. We demonstrated that OCT is a very useful tool to enhance the performance of biometric control systems concerning attacks by thin layer fingerprint fakes.

With the onset of COVID-19 pandemic, wearing of face mask became essential and the face occlusion created by the masks deteriorated the performance of the face biometric systems. In this situation, the use of periocular region (region around the eye) as a biometric trait for authentication is gaining attention since it is the most visible region when masks are used. One important issue in periocular biometrics is the identification of an optimal size periocular ROI which contains enough features for authentication. The state of the art ROI extraction algorithms use fixed size rectangular ROI calculated based on some reference points like center of the iris or centre of the eye without considering the shape of the periocular region of an individual. This paper proposes a novel approach to extract optimum size periocular ROIs of two different shapes (polygon and rectangular) by using five reference points (inner and outer canthus points, two end points and the midpoint of eyebrow) in order to accommodate the complete shape of the periocular region of an individual. The performance analysis on UBIPr database using CNN models validated the fact that both the proposed ROIs contain enough information to identify a person wearing face mask.

Human iris is considered a reliable and accurate modality for biometric recognition due to its unique texture information. Reliability and accuracy of iris biometric modality have prompted its large-scale deployment for critical applications such as border control and national identification projects. The extensive growth of iris recognition systems has raised apprehensions about the susceptibility of these systems to various presentation attacks. In this thesis, a novel iris presentation attack using deep learning based synthetically generated iris images is presented. Utilizing the generative capability of deep convolutional generative adversarial networks and iris quality metrics, a new framework, named as iDCGAN is proposed for creating realistic appearing synthetic iris images. In-depth analysis is performed using quality score distributions of real and synthetically generated iris images to understand the effectiveness of the proposed approach. We also demonstrate that synthetically generated iris images can be used to attack existing iris recognition systems. As synthetically generated iris images can be effectively deployed in iris presentation attacks, it is important to develop accurate iris presentation attack detection algorithms which can distinguish such synthetic iris images from real iris images. For this purpose, a novel structural and textural feature-based iris presentation attack detection framework (DESIST) is proposed. The key emphasis of DESIST is on developing a unified framework for detecting a medley of iris presentation attacks, including synthetic iris. Experimental evaluations showcase the efficacy of the proposed DESIST framework in detecting synthetic iris presentation attacks.

The increasing reliance on Automated Teller Machines (ATMs) has highlighted the urgent need for advanced authentication mechanisms to safeguard user transactions against fraud and unauthorized access. However, traditional methods such as Personal Identification Numbers (PINs) and passwords remain vulnerable to attacks, while unimodal biometric systems face challenges of inter-class variance, environmental interference, and non-universality. Specifically, single-modality approaches and conventional ATM cameras fall short in capturing reliable biometric features under varying conditions, while the effectiveness of bimodal approaches in such environments has not been adequately investigated. Therefore, this study developed a bimodal biometric authentication system integrating face and iris recognition with Gray Level Co-Occurrence Matrix (GLCM) for enhanced ATM security. The system leverages GLCM for powerful texture feature extraction from both modalities, capturing intricate spatial relationships that are difficult to spoof. The extracted feature vectors were used to train Support Vector Machines (SVM) with a Radial Basis Function (RBF) kernel as classifiers for both face and iris recognition. The final authentication decision was made using Boolean OR rule fusion. The system achieved a remarkable accuracy of 98.2%, with a False Acceptance Rate (FAR) of 1.8% and a False Rejection Rate (FRR) of 1.2%. These results demonstrably outperformed comparable unimodal systems and existing biometric ATMs, validating the proposed framework as a highly secure and efficient solution for financial authentication systems.