Zahid Akhtar

Face Recognition under Ageing Effect: A Comparative Analysis

Previous studies indicate that performance of the face recognition system severely degrades under the ageing effect. Despite the rising attention to facial ageing, there exist no comparative evaluation of the existing systems under the impact of ageing. Moreover, the compound effect of ageing and other variate such as glasses, gender etc, that are known to influence the performance, remain overlooked till date. To this aim, the contribution of this work are as follows: 1) evaluation of six baseline facial representations, based on local features, under the ageing effect, and 2) analysis of the compound effect of ageing with other variates, i.e., race, gender, glasses, facial hair etc.

Apache Hama: An Emerging Bulk Synchronous Parallel Computing Framework for Big Data Applications

In today’s highly intertwined network society, the demand for big data processing frameworks is continuously growing. The widely adopted model to process big data is parallel and distributed computing. This paper documents the significant progress achieved in the field of distributed computing frameworks, particularly Apache Hama, a top level project under the Apache Software Foundation, based on bulk synchronous parallel processing. The comparative studies and empirical evaluations performed in this paper reveal Hama’s potential and efficacy in big data applications. In particular, we present a benchmark evaluation of Hama’s graph package and Apache Giraph using PageRank algorithm. The results show that the performance of Hama is better than Giraph in terms of scalability and computational speed. However, despite great progress, a number of challenging issues continue to inhibit the full potential of Hama to be used at large scale. This paper also describes these challenges, analyzes solutions proposed to overcome them, and highlights research opportunities.

Temporal Analysis Of Adaptive Face Recognition

Abstract Aging has profound effects on facial biometrics as it causes change in shape and texture. However, aging remains an under-studied problem in comparison to facial variations due to pose, illumination and expression changes. A commonly adopted solution in the state-of-the-art is the virtual template synthesis for aging and de-aging transformations involving complex 3D modelling techniques. These methods are also prone to estimation errors in the synthesis. Another viable solution is to continuously adapt the template to the temporal variation (ageing) of the query data. Though efficacy of template update procedures has been proven for expression, lightning and pose variations, the use of template update for facial aging has not received much attention so far. Therefore, this paper first analyzes the performance of existing baseline facial representations, based on local features, under ageing effect then investigates the use of template update procedures for temporal variance due to the facial age progression process. Experimental results on FGNET and MORPH aging database using commercial VeriLook face recognition engine demonstrate that continuous template updating is an effective and simple way to adapt to variations due to the aging process.

Face Spoof Attack Recognition Using Discriminative Image Patches

Face recognition systems are now being used in many applications such as border crossings, banks, and mobile payments. The wide scale deployment of facial recognition systems has attracted intensive attention to the reliability of face biometrics against spoof attacks, where a photo, a video, or a 3D mask of a genuine user’s face can be used to gain illegitimate access to facilities or services. Though several face antispoofing or liveness detection methods (which determine at the time of capture whether a face is live or spoof) have been proposed, the issue is still unsolved due to difficulty in finding discriminative and computationally inexpensive features and methods for spoof attacks. In addition, existing techniques use whole face image or complete video for liveness detection. However, often certain face regions (video frames) are redundant or correspond to the clutter in the image (video), thus leading generally to low performances. Therefore, we propose seven novel methods to find discriminative image patches, which we define as regions that are salient, instrumental, and class-specific. Four well-known classifiers, namely, support vector machine (SVM), Naive-Bayes, Quadratic Discriminant Analysis (QDA), and Ensemble, are then used to distinguish between genuine and spoof faces using a voting based scheme. Experimental analysis on two publicly available databases (Idiap REPLAY-ATTACK and CASIA-FASD) shows promising results compared to existing works.

Investigating Apache Hama: a bulk synchronous parallel computing framework

The quantity of digital data is growing exponentially, and the task to efficiently process such massive data is becoming increasingly challenging. Recently, academia and industry have recognized the limitations of the predominate Hadoop framework in several application domains, such as complex algorithmic computation, graph, and streaming data. Unfortunately, this widely known map-shuffle-reduce paradigm has become a bottleneck to address the challenges of big data trends. The demand for research and development of novel massive computing frameworks is increasing rapidly, and systematic illustration, analysis, and highlights of potential research areas are vital and very much in demand by the researchers in the field. Therefore, we explore one of the emerging and promising distributed computing frameworks, Apache Hama. This is a top level project under the Apache Software Foundation and a pure bulk synchronous parallel model for processing massive scientific computations, e.g. graph, matrix, and network algorithms. The objectives of this contribution are twofold. First, we outline the current state of the art, distinguish the challenges, and frame some research directions for researchers and application developers. Second, we present real-world use cases of Apache Hama to illustrate its potential specifically to the industrial community.

Face Anti-spoofing in Biometric Systems

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.

Biometrics: In Search of Identity and Security (Q & A)

Though biometrics is widely being used in various applications, it still faces many challenges. This article aims: i) to present an overview of biometrics and latest progress, ii) to further understanding of general audiences and policy makers, and interdisciplinary research, iii) to complement earlier articles with updates on recent topics.

Visual Nonverbal Behavior Analysis: The Path Forward

Social signal processing (SSP) is a promising automated technology that aims to provide computers with the ability to sense and understand human social behaviors. Representative SSP applications include novel human-computer interaction mechanisms that enhance machine sensitivity of users emotional and mental states, more engaging games, ambient intelligence systems responsive to social context, and new quantitative psychological evaluation tools for coaching or diagnosis. Based on adopted cues, existing SSP methods can be categorized as verbal or nonverbal. Over the last decade, significant progress has been accomplished in visual nonverbal behavior analysis (VNBA). However, several emerging issues such as fusion of multimodal cues, context estimation, and user privacy protection still need to be addressed adequately. The authors present an overview of VNBA and describe various research challenges and proposed solutions.

Mobile biometrics: Towards a comprehensive evaluation methodology

Smartphones have become the pervasive personal computing platform. Recent years thus have witnessed exponential growth in research and development for secure and usable authentication schemes for smartphones. Several explicit (e.g., PIN-based) and/or implicit (e.g., biometrics-based) authentication methods have been designed and published in the literature. In fact, some of them have been embedded in commercial mobile products as well. However, the published studies report only the brighter side of the proposed scheme(s), e.g., higher accuracy attained by the proposed mechanism. While other associated operational issues, such as computational overhead, robustness to different environmental conditions/attacks, usability, are intentionally or unintentionally ignored. More specifically, most publicly available frameworks did not discuss or explore any other evaluation criterion, usability and environment-related measures except the accuracy under zero-effort. Thus, their baseline operations usually give a false sense of progress. This paper, therefore, presents some guidelines to researchers for designing, implementation, and evaluating smartphone user authentication methods for a positive impact on future technological developments.

Intrusion Detection in High-Speed Big Data Networks: A Comprehensive Approach

In network intrusion detection research, two characteristics are generally considered vital to build efficient intrusion detection systems (IDSs) namely, optimal feature selection technique and robust classification schemes. However, an emergence of sophisticated network attacks and the advent of big data concepts in anomaly detection domain require the need to address two more significant aspects. They are concerned with employing appropriate big data computing framework and utilizing contemporary dataset to deal with ongoing advancements. Based on this need, we present a comprehensive approach to build an efficient IDS with the aim to strengthen academic anomaly detection research in real-world operational environments. The proposed system is a representative of the following four characteristics: It (i) performs optimal feature selection using branch-and-bound algorithm; (ii) employs logistic regression for classification; (iii) introduces bulk synchronous parallel processing to handle computational requirements of large-scale networks; and (iv) utilizes real-time contemporary dataset named ISCX-UNB to validate its efficacy.