The locations of the eyes are the most commonly used features to perform face normalisation (i.e. alignment of facial features), which is an essential preprocessing stage of many face recognition systems. In this study, the authors study the sensitivity of open source implementations of five face recognition algorithms to misalignment caused by eye localisation errors. They investigate the ambiguity in the location of the eyes by comparing the difference between two independent manual eye annotations. They also study the error characteristics of automatic eye detectors present in two commercial face recognition systems. Furthermore, they explore the impact of using different eye detectors for training/enrolment and query phases of a face recognition system. These experiments provide an insight into the influence of eye localisation errors on the performance of face recognition systems and recommend a strategy for the design of training and test sets of a face recognition algorithm.

This study presents a multimodal system that optimises and integrates the iris and face features based on fusion at the score level. The proposed multibiometric system has two novelties as compared with the previous work. First, the authors deploy a fuzzy C-means clustering with level set (FCMLS) method in an effort to localise the non-ideal iris images accurately. The FCMLS method incorporates the spatial information into the level set (LS)-based curve evolution approach and regularises the LS propagation locally. The proposed iris localisation scheme based on FCMLS avoids over-segmentation and performs well against blurred iris/sclera boundary. Second, genetic and evolutionary feature extraction (GEFE) is applied towards multimodal biometric recognition. GEFE uses genetic and evolutionary computation to evolve local binary pattern feature extractors to elicit distinctive features from the iris and facial images. Different weights for each modality are investigated to determine the significance of each modality. By using the FCMLS method to segment an iris image accurately, as well as using GEFE on a multibiometric dataset, the authors note improved performance of identification and verification accuracies over subjects on a unimodal dataset. More specifically, on the multimodal dataset of face and iris images, GEFE had an identification accuracy of 100%.

The authors present the author's results of using saccadic eye movements for biometric user verification. The method can be applied to computers or other devices, in which it is possible to include an eye movement camera system. Thus far, this idea has been little researched. As they have extensively studied eye movement signals for medical applications, they saw an opportunity for the biometric use of saccades. Saccades are the fastest of all eye movements, and are easy to stimulate and detect from signals. As signals measured from a physiological origin, the properties of eye movements (e.g. latency and maximum angular velocity) may contain considerable variability between different times of day, between days or weeks and so on. Since such variability might impair biometric verification based on saccades, they attempted to tackle this issue. In contrast to their earlier results, where they did not include such long intervals between sessions of eye movement recordings as in the present research, their results showed that – notwithstanding some variability present in saccadic variables – this variability was not considerable enough to essentially disturb or impair verification results. The only exception was a test series of very long intervals ∼16 or 32 months in length. For the best results obtained with various classification methods, false rejection and false acceptance rates were <5%. Thus, they conclude that saccadic eye movements can provide a realistic basis for biometric user verification.

This study presents optimisations to a three-dimensional (3D) face recognition method the authors published in 2011. The optimisations concern handling and estimation of motion from a single 3D image using the symmetry of the face, fine registration by selection of the maximum score for small variations of the registration parameters and efficient training using automatic outlier removal where only part of the classifier is retrained. The optimisations lead to a staggering performance improvement: the verification rate on Face Recognition Grand Challenge (FRGC) v2 data at false accept rate = 0.1% increases from 94.6 to 99.3% and the identification rate increases from 99 to 99.4%. Both are, to the authors' knowledge, the best scores ever published on the FRGC data. In addition, the registration time was reduced from about 2.5 to 0.2–0.6 s and the number of comparisons has increased from about 11 000 to more than 50 000 per second. For slightly decreased performance, even millions of comparisons can be realised. The fast registration means near real-time recognition with 2–5 images is possible. The optimisations are not specific for this method, but can be beneficial for other 3D face recognition methods as well.

In the past decade, biomedical instrumentations have witnessed major developments and now it is very easy to measure human biomedical electrical signals. One of these signals is the brain waves, known as electroencephalogram (EEG) signals, which became very easy to be measured using portable devices and dry electrodes. This opens the way for the use of brain waves in different applications rather than the biomedical diagnosis. One of the most recent non-medical applications for brain waves is the biometric authentication. Brain waves have some advantages which are not present in the commonly used identifiers, such as face and fingerprints, making them robust to spoof attacks. However, brain waves still face many challenges with reference to permanence and uniqueness. In this study, the authors discuss the employment of brain signals for human recognition tasks and focus on the challenges facing these signals towards the deployment of a practical biometric system. This study, also, provides a comprehensive review of the proposed approaches developed in EEG-based biometric authentication systems.