No description available.

Bibliography: pages 239-248. / This thesis addresses a practical problem. The problem concerns the evaluation of 'identification parades', or 'lineups', which are frequently used by police to secure evidence of identification. It is well recognised that this evidence is frequently unreliable, and has led on occasion to tragic miscarriages of justice. A review of South African law is conducted and reported in the thesis, and shows that the legal treatment of identification parades centres on the requirement that parades should be composed of people of similar appearance to the suspect. I argue that it is not possible, in practice, to assess whether this requirement has been met and that this is a significant failing. Psychological work on identification parades includes the development of measures of parade fairness, and the investigation of alternate lineup structures. Measures of parade fairness suggested in the literature are indirectly derived, though; and I argue that they fail to address the question of physical similarity. In addition, I develop ways of reasoning inferentially (statistically) with measures of parade fairness, and suggest a new measure of parade fairness. The absence of a direct measure of similarity constitutes the rationale for the empirical component of the thesis. I propose a measure of facial similarity, in which the similarity of two faces is defined as the Euclidean distance between them in a principal component space, or representational basis. (The space is determined by treating a set of digitized faces as numerical vectors, and by submitting these to principal component analysis). A similar definition is provided for 'facial distinctiveness', namely as the distance of a face from the origin or centroid of the space. The validity of the proposed similarity measure is investigated in several ways, in a total of seven studies, involving approximately 700 subjects. 350 frontal face images and 280 profile face images were collected for use as experimental materials, and as the source for the component space underlying the similarity measure. The weight of the evidence, particularly from a set of similarity rating tasks, suggests that the measure corresponds reasonably well to perceptions of facial similarity. Results from a mock witness experiment showed that it is also strongly, and monotonically related to standard measures of lineup fairness. Evidence from several investigations of the distinctiveness measure, on the other hand, showed that it does not appear to be related to perceptions of facial distinctiveness. An additional empirical investigation examined the relation between target-foil similarity and identification performance. Performance was greater for lineups of low similarity, both when the perpetrator was present, and when the perpetrator was absent. The consequences of this for the understanding of lineup construction and evaluation are discussed.

The biggest change in the facial recognition community since the completion of the FacE REcognition Technology (FERET) program has been the introduction of facial recognition products to the commercial market. Open market competitiveness has driven numerous technological advances in automated face recognition since the FERET program and significantly lowered system costs. Today there are dozens of facial recognition systems available that have the potential to meet performance requirements for numerous applications. But which of these systems best meet the performance requirements for given applications? Repeated inquiries from numerous government agencies on the current state of facial recognition technology prompted the DoD Counterdrug Technology Development Program Office to establish a new set of evaluations. The Facial Recognition Vendor Test 2000 (FRVT 2000), was co-sponsored by the DoD Counterdrug Technology Development Program Office, the National Institute of Justice, and the Defense Advanced Research Projects Agency, and was administered in May-June 2000. The sponsors of the FRVT 2000 had two major goals for the evaluation. The first was a technical assessment of the capabilities of commercially available facial recognition systems. The sponsors wanted to know the strengths and weaknesses of each individual system, as well as obtain an understanding of the current state of the art for facial recognition. The second goal of the evaluation was to educate the biometrics community and the general public on how to present and analyze results. The sponsors have seen vendors and would-be customers quoting outstanding performance specifications without understanding that these specifications are virtually useless without first knowing the details of the test that was used to produce the quoted results. The Facial Recognition Vendor Test 2000 was a worthwhile endeavor. It will help numerous readers evaluate facial recognition systems for their own uses and will serve as a benchmark for all future evaluations of biometric technologies. The FRVT 2000 evaluations were not designed, and the FRVT 2000 Evaluation Report was not written, to be a buyer's guide for facial recognition. No one will be able to open the report to a specific page to determine which facial recognition system is best because there is not one system for all applications. The only way to determine the best facial recognition system for any application is to follow the three-step evaluation methodology described in the FRVT 2000 Evaluation Report and analyze the data as it pertains to each individual application. This thesis explains the design and implementation of the FRVT 2000 evaluations, and discusses how the FRVT 2000 Evaluation Report met the author's objectives for the evaluation. / Master of Science

Facial recognition methodologies, widely used today in everything from automatic passport controls at airports to unlocking devices on mobile phones, has developed greatly in recent years. The methodologies vary from feature based landmark comparisons in 2D and 3D, utilising Principal Component Analysis (PCA) to surface-based Iterative Closest Point Algorithm (ICP) analysis and a wide variety of techniques in between. The aim of all facial recognition software (FCS) is to find or match a target face with a reference face of a known individual from an existing database. FCS, however, faces many challenges including temporal variations due to development/ageing and variations in facial expression. To determine any quantifiable heritability of facial morphology using this resource, one has to look for faces with enough demonstrable similarities to predict a possible genetic link, instead of the ordinary matching of the same individual’s face in different instances. With the exception of identical twins, this means the introduction of many more variables into the equation of how to relate faces to each other. Variation due to both developmental and degenerative aging becomes a much greater issue than in previous matching situations, especially when comparing parents with children. Additionally, sexual dimorphism is encountered with cross gender relationships, for example, between mothers and sons. Non-inherited variables are also encountered such as BMI, facial disfigurement and the effects of dental work and tooth loss. For this study a Trimmed Iterative Closest Point Algorithm (TrICP) was applied to three-dimensional surfaces scans, created using a white light scanner and Flexscan 3D, of the faces of 41 families consisting of 139 individuals. The TrICP algorithm produced 7176 Mesh-to-mesh Values (MMV) for each of seven sections of the face (Whole face, Eyes, Nose, Mouth, Eyes-Nose, Eyes-Nose-Mouth, and Eyes-Nose- Mouth-Chin). Receiver Operated Characteristic (ROC) analysis was then conducted for each of the seven sections of the face within 11 predetermined categories of relationship, in order to assess the utility of the method for predicting familial relationships (sensitivity/specificity). Additionally, the MMVs of three single features, (eyes, nose and mouth) were combined to form four combination areas which were analysed within the same 11 relationship categories. Overall the relationship between sisters showed the most similarity across all areas of the face with the clear exception of the mouth. Where female to female comparison was conducted the mouth consistently negatively affected the results. The father-daughter relationship showed the least similarity overall and was only significant for three of the 11 portions of the face. In general, the combination of three single features achieved greater accuracy as shown by Areas Under the Curve (AUC) than all other portions of the face and single features were less predictive than the face as a whole.

This thesis presents techniques for locating landmarks in images of human faces. A modified Active Shape Model (ASM [21]) is introduced that uses a form of SIFT descriptors [68]. Multivariate Adaptive Regression Splines (MARS [40]) are used to efficiently match descriptors around landmarks. This modified ASM is fast and performs well on frontal faces. The model is then extended to also handle non-frontal faces. This is done by first estimating the face's pose, rotating the face upright, then applying one of three ASM submodels specialized for frontal, left, or right three-quarter views. The multiview model is shown to be effective on a variety of datasets.

This research aimed to explore and contextualise research on the electrophysiological potentials evoked in response to human face recognition within the South African context. Previous research provides evidence that there is a measurable difference in the electrophysiological response to faces of people of other racial groups when compared to the response to one’s own race group. The difference is seen in greater peak amplitudes in response to one’s own-race (indicating greater attention being granted) in comparison to the other-race. This has been labelled the Cross-Race Effect. This research also attempted to expand on previous research in the use of a mixed-race sample and realistic colour images, in contrast to previously used greyscale images. A purposive sample of 40 students at the University of the Witwatersrand was split equally between gender and race (Black and White) with an Indian control group. The electrical potentials elicited by the facial stimuli were extracted from the ongoing electroencephalograms. The results obtained displayed inverse results to those found internationally, with Black participants eliciting no differences between racial groups, and White participants eliciting a greater peak amplitude to Black (other-race) faces. A gender effect was also seen, with White participants eliciting greater peak amplitudes towards female faces, while Black participant again showed no differences between male and female faces. Trends displayed in the results, and the significance thereof, are discussed, and the importance of the effect of society of developmental neurology is highlighted, with the rephrasing of cultural neuroscience to Socio-Cultural Neuroscience. The results ultimately suggest that the internationally seen cross-race effect is absent in a young South African population (with the principle of increased exposure leading to increased attention still in effect), indicating that South Africa is beginning to move away from racial discrimination, and moving towards a future of true integration and equality.

The present collection of studies examined the development of the ability to recognize facial identity rapidly and accurately, using two complementary approaches: comparing the performance of children and adults, and by training observers to learn novel stimuli in a laboratory setting. Across studies, children 8 to 10 years old performed less accurately than adults, a finding that confirms previous research that face processing takes many years to develop. However, results from two studies suggest that by 8 years of age, children encode individual facial identities relative to the average of previously experienced faces, in a manner similar to adults. The findings suggest that the basic mental architecture supporting face recognition is in place by 8 years. Additionally, children improved their ability to recognize unfamiliar faces from various viewpoints after just two, one-hour sessions of training, although the rate of learning was more variable than that observed in adults. The results from two studies also revealed that children's recognition accuracies of facial identity were lower than those of adults. An examination of children's similarity judgments of facial identity revealed that such immaturities in children's face processing may stem from greater variability in the mental representation of facial identities, rather than from immaturities in the encoding process per se. Findings from a final study suggest that the ability to make fine perceptual discriminations among individual faces arises, in part, from experience differentiating faces at the individual level, unlike the experience with non-face objects that typically involves recognition at the category level. The findings from the studies presented in this thesis suggest that such perceptual expertise may arise only with years of experience recognizing individual faces, and with sufficient neural development to support a stable mental representation of individual facial identities. / Thesis / Doctor of Philosophy (PhD)

Yes / The application of computer vision in face processing remains an important research field. The aim of this chapter is to provide an up-to-date review of research efforts of computer vision scientist in facial image processing, especially in the areas of entertainment industry, surveillance, and other human computer interaction applications. To be more specific, this chapter reviews and demonstrates the techniques of visible facial analysis, regardless of specific application areas. First, the chapter makes a thorough survey and comparison of face detection techniques. It provides some demonstrations on the effect of computer vision algorithms and colour segmentation on face images. Then, it reviews the facial expression recognition from the psychological aspect (Facial Action Coding System, FACS) and from the computer animation aspect (MPEG-4 Standard). The chapter also discusses two popular existing facial feature detection techniques: Gabor feature based boosted classifiers and Active Appearance Models, and demonstrate the performance on our in-house dataset. Finally, the chapter concludes with the future challenges and future research direction of facial image processing. © 2011, IGI Global.

A set of subsets is said to have the Helly property if the condition that each pair of subsets has a non-empty intersection implies that the intersection of all subsets has a non-empty intersection. In 1966, Gallai noticed that the set of all longest paths of a connected graph is pairwise intersecting and asked if the set had the Helly property. While it is not true in general, a number of classes of graphs have been shown to have the property. In this dissertation, we show that K4-minor-free graphs, interval graphs, circular arc graphs, and the intersection graphs of spider graphs are classes that have this property. The accuracy of facial recognition algorithms on images taken in controlled conditions has improved significantly over the last two decades. As the focus is turning to more unconstrained or relaxed conditions and toward videos, there is a need to better understand what factors influence performance. If these factors were better understood, it would be easier to predict how well an algorithm will perform when new conditions are introduced. Previous studies have studied the effect of various factors on the verification rate (VR), but less attention has been paid to the false accept rate (FAR). In this dissertation, we study the effect various factors have on the FAR as well as the correlation between marginal FAR and VR. Using these relationships, we propose two models to predict marginal VR and demonstrate that the models predict better than using the previous global VR.

E-learning and particularly distance-based learning is becoming an increasingly important mechanism for education. A leading Virtual Learning Environment (VLE) reports a user base of 70 million students and 1.2 million teachers across 7.5 million courses. Whilst e-learning has introduced flexibility and remote/distance-based learning, there are still aspects of course delivery that rely upon traditional approaches. The most significant of these is examinations. The lack of being able to provide invigilation in a remote-mode has restricted the types of assessments, with exams or in-class test assessments proving difficult to validate. Students are still required to attend physical testing centres in order to ensure strict examination conditions are applied. Whilst research has begun to propose solutions in this respect, they fundamentally fail to provide the integrity required. This thesis seeks to research and develop an e-invigilator that will provide continuous and transparent invigilation of the individual undertaking an electronic based exam or test. The analysis of the e-invigilation solutions has shown that the suggested approaches to minimise cheating behaviours during the online test have varied. They have suffered from a wide range of weaknesses and lacked an implementation achieving continuous and transparent authentication with appropriate security restrictions. To this end, the most transparent biometric approaches are identified to be incorporated in an appropriate solution whilst maintaining security beyond the point-of-entry. Given the existing issues of intrusiveness and point-of-entry user authentication, a complete architecture has been developed based upon maintaining student convenience but providing effective identity verification throughout the test, rather than merely at the beginning. It also provides continuous system-level monitoring to prevent cheating, as well as a variety of management-level functionalities for creating and managing assessments including a prioritised and usable interface in order to enable the academics to quickly verify and check cases of possible cheating. The research includes a detailed discussion of the architecture requirements, components, and complete design to be the core of the system which captures, processes, and monitors students in a completely controlled e-test environment. In order to highlight the ease of use and lightweight nature of the system, a prototype was developed. Employing student face recognition as the most transparent multimodal (2D and 3D modes) biometrics, and novel security features through eye tracking, head movements, speech recognition, and multiple faces detection in order to enable a robust and flexible e-invigilation approach. Therefore, an experiment (Experiment 1) has been conducted utilising the developed prototype involving 51 participants. In this experiment, the focus has been mainly upon the usability of the system under normal use. The FRR of those 51 legitimate participants was 0 for every participant in the 2D mode; however, it was 0 for 45 of them and less than 0.096 for the rest 6 in the 3D mode. Consequently, for all the 51 participants of this experiment, on average, the FRR was 0 in 2D facial recognition mode, however, in 3D facial recognition mode, it was 0.048. Furthermore, in order to evaluate the robustness of the approach against targeted misuse 3 participants were tasked with a series of scenarios that map to typical misuse (Experiment 2). The FAR was 0.038 in the 2D mode and 0 in the 3D mode. The results of both experiments support the feasibility, security, and applicability of the suggested system. Finally, a series of scenario-based evaluations, involving the three separate stakeholders namely: Experts, Academics (qualitative-based surveys) and Students (a quantitative-based and qualitative-based survey) have also been utilised to provide a comprehensive evaluation into the effectiveness of the proposed approach. The vast majority of the interview/feedback outcomes can be considered as positive, constructive and valuable. The respondents agree with the idea of continuous and transparent authentication in e-assessments as it is vital for ensuring solid and convenient security beyond the point-of-entry. The outcomes have also supported the feasibility and practicality of the approach, as well as the efficiency of the system management via well-designed and smart interfaces.