Cameras constantly capture and track facial images and videos on cell phones, webcams etc. In the past decade, facial expression classification and recognition has been the topic of interest as facial expression analysis has a wide range of applications such as intelligent tutoring system, systems for psychological studies etc. This study reviews the latest advances in the algorithms and techniques used in distinct phases of real-time facial expression recognition. Though there are state-of-art approaches to address facial expression identification in real-time, many issues such as subjectivity-removal, occlusion, pose, low resolution, scale, variations in illumination level and identification of baseline frame still remain unaddressed. Attempts to deal with such issues for higher accuracy lead to a trade-off in efficiency. Furthermore, the goal of this study is to elaborate on these issues and highlight the solutions provided by the current approaches. This survey has helped the authors to understand that there is a need for a better strategy to address these issues without having to trade-off performance in real-time.

This study introduces an approach for user authentication using free-text keystroke dynamics which incorporates text in Arabic language. The Arabic language has completely different characteristics to those of English. The approach followed in this study involves the use of the keyboard's key-layout. The method extracts timing features from specific key-pairs in the typed text. Decision trees were exploited to classify each of the users’ data. In parallel for comparison, support vector machines were also used for classification in association with an ant colony optimisation feature selection technique. The results obtained from this study are encouraging as low false accept rates and false reject rates were achieved in the experimentation phase. This signifies that satisfactory overall system performance was achieved by using the typing attributes in the proposed approach, while typing Arabic text.

The ‘fuzzy vault scheme’ is a cryptographic primitive being considered for storing fingerprint minutiae protected. A well-known problem of the fuzzy vault scheme is its vulnerability against correlation attack-based cross-matching thereby conflicting with the ‘unlinkability requirement’ and ‘irreversibility requirement’ of effective biometric information protection. Yet, it has been demonstrated that in principle a minutiae-based fuzzy vault can be secured against the correlation attack by passing the to-be-protected minutiae through a quantisation scheme. Unfortunately, single fingerprints seem not to be capable of providing an acceptable security level against offline attacks. To overcome the aforementioned security issues, this study shows how an implementation for multiple fingerprints can be derived on basis of the implementation for single finger thereby making use of a Guruswami–Sudan algorithm-based decoder for verification. The implementation, for which public C++ source code can be downloaded, is evaluated for single and various multi-finger settings using the MCYT-Fingerprint-100 database and provides security-enhancing features such as the possibility of combination with password and a slow-down mechanism.

Capturing age and sex of subjects from whole-body features has important applications in a wide variety of areas. However, current techniques for determining this information without subject interaction or high-resolution images are problematic. While computer vision techniques (e.g. poselets and histogram-oriented gradients) are functional at a stand-off, these methods often include areas influenced by characteristics such as clothing or hairstyle which vary by region and culture. Whole-body anthropometrics, especially those of children and youth experiencing rapid musculoskeletal changes, may help inform robust models of age estimation and sex classification. Models of anthropometric variables were developed from a pre-existing database for age estimation using linear regression techniques. Sex classification was performed both over the entire subject group as well as three individual age bins (2 ≤ subject age < 8, 8 ≤ subject age < 14, and 14 ≤ subject age). Age estimation models were highly dependent on head size and exhibited r-squared values as high as 0.91 and root mean square error values as low as 1.29 years. Sex classification was found to be highly linked to a combination of foot, hand, hip, and torso metrics for correct classification as high as 88%. The results presented herein may help develop and focus methods of determining age and sex.

The handwritten signature is a biometric method used to verify a person's identity. This study lies within the scope of an online handwritten signature verification system, in which a signature is modelled by an analytical approach based on the empirical mode decomposition. The organised system is tested on the SVC2004 task1 and MYCT-100 databases. The implemented evaluation protocol shows the importance of the adopted method and allows obtaining an equal error rate of 1.83 and 2.23% for the SVC2004 task1 and the MYCT-100 databases, respectively.

In this study the authors will look at the detection and segmentation of the iris and its influence on the overall performance of the iris-biometric tool chain. The authors will examine whether the segmentation accuracy, based on conformance with a ground truth, can serve as a predictor for the overall performance of the iris-biometric tool chain. That is: If the segmentation accuracy is improved will this always improve the overall performance? Furthermore, the authors will systematically evaluate the influence of segmentation parameters, pupillary and limbic boundary and normalisation centre (based on Daugman's rubbersheet model), on the rest of the iris-biometric tool chain. The authors will investigate if accurately finding these parameters is important and how consistency, that is, extracting the same exact region of the iris during segmenting, influences the overall performance.

In this study, the authors present two new techniques with their own particular advantages dedicated to the authentication of a person based on the three-dimensional geometry of the cornea. A device known as corneal topographer is used for capturing the shape of each cornea. Until now only a few studies on corneal biometry have been conducted and they were limited only to the anterior surface. In this study, since the whole cornea is a tissue layered by two (anterior and posterior) surfaces, the authors propose to use both surfaces to characterise the corneal shape. The first proposed method consists of comparing coefficients from a spherical harmonics decomposition, and this allows to do a fast comparison that can be used to perform many-to-one comparisons. The second approach is based on the minimal residual volume between two corneas after a registration step, this geometry-based method is more accurate but slower, and is thus used to perform one-to-one comparisons. A cascade fusion scheme is also proposed to benefit from the advantages of both methods. The authors’ study demonstrates that corneal shape could be used for biometry. The two proposed methods have been tested and validated on a dataset of 257 corneas.

Several cancellable biometrics (CBs) techniques have been proposed to protect biometric data and maintain users’ privacy. Although such techniques can withstand brute-force and/or pre-image attacks, they are vulnerable to correlation attacks. In this study, the authors propose a novel correlation attack-resistant CBs scheme that is based on a convolution operation and a bidirectional associative memory (BAM) neural network. The proposed scheme utilises BAM to bind biometric templates to random bit-strings in a secure and efficient manner. These random bit-strings are then employed to derive cancellable templates from the true templates linked to them via BAM weights, which are safely stored with the generated cancellable template in the system database. In this study, linear convolution is adopted as the cancellable transformation process. The result of convolving the original biometric template with the transformation key is binarised according to a predefined threshold to thwart blind de-convolution. The security of the proposed scheme against different attacks is analysed and experiments on the CASIA-IrisV3-Interval dataset illustrate the efficacy of the proposed scheme.

Nowadays, biometrics-based authentication is playing a potential approach for many modern applications such as banking, homeland security etc. However, the end-users may feel uncomfortable to deploy this technology because of not well-solved accurate rate and security problems. To overcome these issues, some significant techniques have been proposed such as biometric template protection, reducing biometric extraction noise etc. Fuzzy vault is one of the most popular methods for biometric template security, which binds a secret key with biometric features and produces one kind of data, called the helper data, for recovering the secret key. Unfortunately, the major drawback of this approach is the lacking of cancellable property. Furthermore, most of the fuzzy vault schemes are performed on two biometrics modalities: fingerprints and iris. Some techniques were introduced to transform the original biometric feature to cancellable one. However, the computational cost of these proposals was quite large. In this research, the authors introduce a periodic transformation attached to fuzzy vault to produce the new cancellable scheme. Their transformation is not only simpler but also suitable for many kinds of biometrics modalities. The experiments demonstrate that this approach is practical with a little better error rate in comparison with the original biometric feature.

Although current face recognition systems in biometrics field are accurate enough to be used as substitutes for passwords or keys, most of them are prone to face spoofing attacks. Different techniques for face spoofing identification have been researched but most of them introduce additional sensors and are not cost or computationally efficient. In this study, the authors study the possibility of using individual differences in facial expressions for improving a face recognition system and make it immune to spoofing attacks. The authors develop a soft biometric neural-network-based system for video-based face recognition by analysing patterns in individual facial expressions on multiple frames. Results show that such a system is possible and has accuracies higher than 85%. Used alongside with a standard principal component analysis-based face recognition system, the combined method achieved 94.5% accuracy on Honda/UCSD Video Database and 92.9% on Youtube Faces DB, comparable with state-of-the-art. When tested against photo spoofing attacks on three public anti-spoofing databases the proposed method was immune. In terms of video spoofing, the error rate for the authors’ proposed method was 1% surpassing state-of-the-art methods.

Fingerprint quality assessment (FQA) has been a challenging issue due to a variety of noisy information contained in the samples, such as physical defect and distortions caused by sensing devices. Existing studies have made efforts to find out more suitable techniques for assessing fingerprint quality but it is difficult to achieve a common solution because of, for example, different image settings. This study is two-fold, related to FQA, including a literature review of the prior work in assessing fingerprint image quality and the associated evaluation approaches. First, the authors categorised some representative studies proposed in last few decades to show how this problem has been solved so far. Second, this study gives a brief introduction of the associated evaluation approaches, and then contributes an extended evaluation framework based on the enrolment selection, which offers repeatable and statistically convincing measures for evaluating quality metrics. Experimental results demonstrate the usability of the proposed evaluation framework via offline trials.

An ear recognition system represents a powerful tool in forensic applications. Even in case the facial characteristic of a suspect is partly or fully covered an image of the outer ear may suffice to reveal a subject's identity. In forensic scenarios imagery may stem from surveillance cameras of environments where image compression is common practice to overcome limitations of storage or transmission capacities. Yet, the impact of severe image compression on ear recognition has remained undocumented. In this work the authors analyse the influence of different state-of-the-art image compression standards on ear detection and ear recognition algorithms. Evaluations conducted on an uncompressed ear database are considered with respect to different stages in the processing chain of an ear recognition system where compression may be applied, representing the most relevant forensic scenarios. Experimental results are discussed in detail highlighting the potential and limitations of automated ear recognition in presence of image compression.