Biometric Security and Privacy

This article chiefly focuses on Fingerprint Quality Assessment (FQA) applied to the Automatic Fingerprint Identification System (AFIS). In our research work, different FQA solutions proposed so far are compared by using several quality metrics selected from the existing studies. The relationship between the quality metric and the matching performance is specifically analyzed via such a comparison and an extra discussion based on the sample utility. This study is achieved via an interoperability analysis by using two different matching tools. Experimental results represented by the global Equal Error Rate (EER) further reveal the constraint of the existing quality assessment solutions in predicting the matching performance. Experiments are performed via several public-known fingerprint databases.

Biometric recognition using hand vein patterns is a relatively new technology that has showed a lot of promise from its inception, with features matching or even exceeding well-established biometric methods. Parameters such as universality, permanence, degree of acceptance, or collectability place vein pattern recognition in the top echelon of biometric methods and still, the technology has not gained the traction heralded in the beginning. The novelty of the domain and the low-entry price point for developing hardware scanning devices have created an opposite effect, where the lack of standardization, low amount of usable hand vein samples, and the over-optimization of the detection algorithms have not yielded significant practical solutions for mainstream integration of the technology. The chapter addresses hand vein patterns—with an emphasis on the veins on the back of the hand—and contains a combination of novel research and analysis/discussion regarding the state of hand vein pattern recognition, its challenges, and potential modern approaches for mitigating the inherent problems of the technology. Closing remarks attempt to picture a possible future roadmap for vein pattern recognition and its inclusion in a permanently connected world.

Biometric technology is an emerging field of information technology that recognizes a person based on a feature vector derived from specific physiological or behavioral characteristic that the person possesses. In the last few years, several works in the field of biometrics got to improve the identification system performance rather than the traditional methods. So far, with the pace of rapid evolution in these works, new biometric modality (palmprint) is appearing to make the process of identification more efficient. There are a number of studies addressing the palmprint modality and the majority of these studies are mainly based on image captured under visible light. However, multispectral imaging technology has been recently used to improve the performance of biometric system. Furthermore, the feature extraction phase plays an important role in the biometric system. For that, several researchers are focused on methods used to extract the majorities of the characteristics that can discriminate each modality, which can decrease the intra-class variability and increase the inter-class variability. In this context and with the growing interest in biometrics applications, the studies in this chapter try to combine the multispectral imaging of palmprint and a new feature extraction method, called PCANet deep learning, in order to improve the system accuracy. To evaluate the performance of the proposed scheme, a database containing palmprint images was required. Thus, experiments were performed using two popularly databases: PolyU and CASIA databases.

This chapter deals with the holistic development of a biometric system based on acoustic ear recognition. Its main purpose is to map and investigate the many aspects within acoustic ear recognition, and based on the most influential ones, make attempts on deducing well performing recognition systems. Fifty subjects have participated in experiments collecting biometric samples. The measuring device composed of a pair of headphones with an integrated microphone as sensor. Several methods have been utilized for feature extraction, including principal component analysis, and various types of distance metrics and classifiers have been employed.

In this chapter, the feasibility of using eye blinking Electro-Oculo-Gram (EOG) signal as a new biometric trait for human identity recognition is tested. For this purpose, raw Electro-Encephalo-Gram (EEG) signals were recorded from 40 volunteers while performing the task of eye blinking. These signals were recorded using portable EEG headset, known as Neurosky Mindwave, which has wireless and dry electrodes at Fp1 position above the left eye. This makes it practical for biometric applications and for measuring EOG signals. For pre-processing, Discrete Wavelet Transform (DWT) is adopted to isolate EOG signals from brainwaves. Then, the onset and the offset of the eye blinking waveforms in the EOG signals are detected. After that, features are extracted using time delineation of the eye blinking waveform where important marks like the amplitude, position, and duration of the positive and negative pulses of the eye blinking waveform are employed as features. Finally, Discriminant Analysis (DA) classifier is used for classification. Moreover, a feature selection technique based on differential evolution is added for the proposed system. The best Correct Recognition Rate (CRR) achieved is 93.75 %. In verification mode, the lowest Equal Error Rate (EER) achieved is 7.45 %. Also, the permanence issue is evaluated using training and testing samples with different time separation between them. The optimistic results achieved in this chapter direct the scientific research to study different approaches for human identification using eye blinking to increase system’s performance. Moreover, eye blinking EOG biometric trait can be fused with other traits like EEG signals to build a multi-modal system to improve the performance of the EEG-based biometric authentication systems.

Gait recognition aims to identify people through the analysis of the way they walk. The challenge of model-free based gait recognition is to cope with various intra-class variations such as clothing variations, carrying conditions, and angle variations that adversely affect the recognition performance. This chapter proposes a method to select the most discriminative human body part based on group Lasso of motion to reduce the intra-class variation so as to improve the recognition performance. The proposed method is evaluated using CASIA gait database (dataset B), and the experimental results suggest that our method yields 88.75 % of Correct Classification Rate (CCR) when compared to existing state-of-the-art methods.

With the wide adoption of smartphones, touchscreens have become the leading input method on the mobile platform, with more than 78 % of all phones using a touchscreen. Thus, more research studies started focusing on touch dynamics and its applications on user authentication. Generally, touch dynamics can be described as the characteristics of the inputs received from a touchscreen when a user is interacting with a device (e.g., a touchscreen mobile phone). Intuitively, touch dynamics is different from keystroke dynamics in that touch dynamics has more input types such as multi-touch and touch movement. On the other hand, the inputs of press button up and press button down in keystroke dynamics are similar to the actions of touch press up and touch press down (e.g., single-touch) in touch dynamics. Due to its characteristics, touch dynamics received more attention from the literature. In this chapter, we aim to present a review, introducing recent advancement relating to touch dynamics in the literature, and providing insights about its future trends in the big data era.

Electrocardiogram (ECG) waveforms hold valuable and critical information that can be used in connected health where privacy can be as important as vitality. A secure connected health solution for human identification is presented in this chapter. The recognition of patients uses ECG biometric data streaming while the ECG signals are encrypted and decrypted using the advanced encryption standard (AES). Three different ECG databases representing 2372 samples are used. The Xilinx ZC702 Zynq based platform is used for the hardware implementation of the proposed system. High level synthesis is used to develop and implement different IP-cores corresponding to various block of the system including the AES cipher, AES decipher, and recognition blocks. In addition, various ECG identification algorithms [i.e., principal component analysis along with Euclidian distance, k-nearest neighbors, and extended nearest neighbor] are implemented and evaluated before hardware implementation. Finally, hardware implementation results have shown that the real-time requirements have been met. Furthermore, the presented solution outperforms current field programmable gate array based systems in terms of processing time, power consumption, and hardware resources usage. Using the most optimized hardware implementation, a single ECG signal can be processed in 10.71 ms while the system uses 30 % of all available resources on the chip and consumes only 107 mW. Moreover, the classification accuracy is between 94 % and 100 % depending on the classifier and on the dataset used.

Offline signature verification is undeniably a prominent aspect of the biometric research. It has many applications, including banking and forensics. Signature verification task involves a comparison of questioned signature with a set of one or more reference signatures. The questioned signature may be genuine (written by the authentic writer), a forgery (written by a different person) or a disguise (written by the authentic writer with some modifications with the intent of a later denial). Signature verification generally encompasses the two main steps: feature extraction and classification. The system performance is primarily dependent on the feature extraction step because the characterising features distinguish between genuine, disguised and forged signatures. In this study, we propose several geometric and colour features to characterise the signatures. The features are combined using random forests, logistic regression and generalised linear models. The results are reported on the datasets of several competitions, including ICDAR 2009, ICFHR 2010, ICDAR 2011 and ICFHR 2012 signature verification competitions. The proposed method generally outperforms the other participating methods.

The performance of automatic person identification based on visual appearance significantly suffers under occlusions in many real life situations. These occlusions may be unintentional due to the use of different items such as head gear, headphone, head scarf, or may also be caused by the style of clothing or just hair style. Intentional facial occlusions occur when a particular person try to hide his identity by hiding his face and appearance from the security cameras. In many incidents captured by surveillance videos, it has been observed that the offenders have covered their appearance and faces from the camera, leaving only the small region around the eyes known as “periocular region.” It is because the periocular region cannot be covered to maintain proper vision. In this chapter we present an extensive study on periocular region based person identification using videos in the visible spectrum, near IR range, and also by using the hyperspectral image cubes in a relatively wider bandwidth. While most of the existing techniques for periocular recognition from videos have handpicked a single best frame from videos, we formulate periocular region based person identification in video as an image-set classification problem. For thorough analysis, we perform experiments on periocular regions extracted automatically from RGB videos, NIR videos, and hyperspectral image cubes. Each image-set is represented by four heterogeneous feature types and classified with six state-of-the-art image-set classification algorithms. We will discuss in detail our novel two stage inverse Error Weighted Fusion algorithm for feature and classifier score fusion. We observe that the proposed two stage fusion is superior to single stage fusion. Comprehensive experimental results are presented on four publicly available datasets including Multiple Biometric Grand Challenge (MBGC) NIR, MBGC visible spectrum dataset both by NIST, Carnegie Mellon University (CMU) Hyperspectral face database (Tech. Report CMURI-TR-02-25), and University of Beira Interior Periocular (UBIPr) dataset. In these experiments excellent recognition on all of the four datasets has been observed. These results are significantly better than the result of most of the existing state-of-the-art methods on the same datasets and under similar experimental setup. In addition to these improvements, we demonstrate the feasibility of image-set based periocular biometrics for real world applications. Deployment of security systems with periocular region based person identification algorithm will reduce the vulnerability of security systems to be hacked by non-cooperative individuals.

The role of collaboration between classes is a key to capture discriminative information among the different classes of image samples and can lead to very good and robust recognition rates. One of the modern approaches that make full use of the collaboration among classes in defining the query sample is Collaborative Representation with regularized least square (CRC-RLS). But, it uses the image intensity features to represent the template and query images and is susceptible to changes in illumination and alignment of cropped faces. Local binary patterns (LBP) have emerged as a very powerful discriminative texture descriptor in representing images and are widely used in state-of-the-art algorithms in terms of acquiring higher accuracies as compared to other descriptors. Multi-scale LBP extends the local binary pattern to multi-scale representation. In this chapter, multi-resolution LBP is employed with CRC-RLS to handle problems associated with face recognition such as illumination, occlusion, disguise, etc. In addition, a kernel version of CRC-RLS is also proposed. The efficacy of our proposed KCRC-RLS is evaluated on four challenging image databases, i.e., AR, Extended Yale B, FERET and ORL capturing a different set of problems including illumination, gesture, occlusion, small pose, etc. The results on all databases indicate a significant improvement in comparison to leading approaches like linear regression (LRC), sparse representation (SRC).

Presently, 3D face recognition researched solutions confronted the problem of recognizing 2D. In our contribution, we specifically discuss major difficulties further to propose and test a novel solution of 3D face recognition that is significantly capable to perform the recognition subject, in cases where the analysis of only a part of the face. With the proposed approach, the distinctive features of the face are captured by first extracting SIFT keypoints on the face of analysis and measure how the face changes along profiles built between pairs of keypoints, second we applied the operator SIFT on LBPP,R images, separately. Following the work of Faltemier and al. then Tang and al., we can better detect a number of keypoints by using SIFT on LBPP, R images, than using SIFT on the original images. The contribution is tested using the whole of the Face Recognition Grand Challenge FRGC v1.0 data. Finally, we perform a classification based on SVM process.

Despite the great deal of progress in face recognition, current systems are vulnerable to spoofing attacks. Several anti-spoofing methods have been proposed to determine whether there is a live person or an artificial replica in front of the camera of face recognition system. Yet, developing efficient protection methods against this threat has proven to be a challenging task. In this chapter, we present a comprehensive overview of the state-of-the-art in face spoofing and anti-spoofing, describing existing methodologies, their pros and cons, results and databases. Moreover, after a comprehensive review of the available literature in the field, we present a new face anti-spoofing method based on color texture analysis, which analyzes the joint color-texture information from the luminance and the chrominance channels using color local binary pattern descriptor. The experiments on two challenging spoofing database exhibited excellent results. In particular, in inter-database evaluation, the proposed approach showed very promising generalization capabilities. We hope this case study stimulates the development of generalized face liveness detection. Lastly, we point out some of the potential research directions in face anti-spoofing.

With the emergence of biometric authentication systems, template protection for biometrics captured attention in the recent years. The privacy concern arises due to storage and misuse of biometric data in various applications. This chapter systematically reviews the published literature on Biometric Template Protection (BTP) during 2005–2016 and covers the methods described in more than hundred articles. It aims to present the current status of BTP schemes by a methodical analysis and taxonomy of BTP approaches, modalities, the fusion of modalities (multi-modal), and hybrid methods. It also presents research implications and extraction outcomes of Systematic Literature Review conducted on BTP schemes. This research work helps researchers and practitioners to find relevant information on BTP methods thereby reducing time and complexity in searching the appropriate studies.

Cybersecurity threats are serious, costly and challenging because they are various, evolutive and easily spread. This chapter is dedicated to brief these issues, its evolution and the various solutions provided by the researchers; it also surveys the biometric solutions to one of the key issues of cybersecurity which is the intrusion, by providing robust authentication solutions basing on the unique physical and behavioural characteristics of the user.

Since 1995, with the Directive 95/46/EC of the European Parliament and the Council, the European Union has established minimum rules concerning the protection of personal data. It tried to reach equilibrium between the protection of fundamental rights of the individuals and the demands of security, justice and economy. However, the rapid technological developments experienced since then brought to surface a completely different state of affairs. The aim of this chapter is to appraise the significance of the new legislative path taken by the European Union insofar biometric data is concerned.