We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by C1-minimization, we propose a general classification algorithm for (image-based) object recognition. This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims.

/pdf/robust-face-recognition-via-sparse-representation-4bfqv6y74o.pdf

Robust Face Recognition via Sparse Representation

As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially during the past several years. At least two reasons account for this trend: the first is the wide range of commercial and law enforcement applications, and the second is the availability of feasible technologies after 30 years of research. Even though current machine recognition systems have reached a certain level of maturity, their success is limited by the conditions imposed by many real applications. For example, recognition of face images acquired in an outdoor environment with changes in illumination and/or pose remains a largely unsolved problem. In other words, current systems are still far away from the capability of the human perception system.This paper provides an up-to-date critical survey of still- and video-based face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. To provide a comprehensive survey, we not only categorize existing recognition techniques but also present detailed descriptions of representative methods within each category. In addition, relevant topics such as psychophysical studies, system evaluation, and issues of illumination and pose variation are covered.

Face recognition: A literature survey

Part I. Experimental Studies: 2. Experiment in psychology 3. Experiments on perceiving III Experiments on imaging 4-8. Experiments on remembering: (a) The method of description (b) The method of repeated reproduction (c) The method of picture writing (d) The method of serial reproduction (e) The method of serial reproduction picture material 9. Perceiving, recognizing, remembering 10. A theory of remembering 11. Images and their functions 12. Meaning Part II. Remembering as a Study in Social Psychology: 13. Social psychology 14. Social psychology and the matter of recall 15. Social psychology and the manner of recall 16. Conventionalism 17. The notion of a collective unconscious 18. The basis of social recall 19. A summary and some conclusions.

Remembering. A Study in Experimental and Social Psychology, Cambridge (University Press) 1964.

An approach to the detection and identification of human faces is presented, and a working, near-real-time face recognition system which tracks a subject's head and then recognizes the person by comparing characteristics of the face to those of known individuals is described. This approach treats face recognition as a two-dimensional recognition problem, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-D characteristic views. Face images are projected onto a feature space ('face space') that best encodes the variation among known face images. The face space is defined by the 'eigenfaces', which are the eigenvectors of the set of faces; they do not necessarily correspond to isolated features such as eyes, ears, and noses. The framework provides the ability to learn to recognize new faces in an unsupervised manner. >

/pdf/face-recognition-using-eigenfaces-163pb1t759.pdf

Face recognition using eigenfaces

We propose that the crucial difference between human cognition and that of other species is the ability to participate with others in collaborative activities with shared goals and intentions: shared intentionality. Participation in such activities requires not only especially powerful forms of intention reading and cultural learning, but also a unique motivation to share psychological states with oth- ers and unique forms of cognitive representation for doing so. The result of participating in these activities is species-unique forms of cultural cognition and evolution, enabling everything from the creation and use of linguistic symbols to the construction of social norms and individual beliefs to the establishment of social institutions. In support of this proposal we argue and present evidence that great apes (and some children with autism) understand the basics of intentional action, but they still do not participate in activities involving joint intentions and attention (shared intentionality). Human children's skills of shared intentionality develop gradually during the first 14 months of life as two ontogenetic pathways intertwine: (1) the general ape line of understanding others as animate, goal-directed, and intentional agents; and (2) a species-unique motivation to share emotions, experience, and activities with other persons. The develop- mental outcome is children's ability to construct dialogic cognitive representations, which enable them to participate in earnest in the collectivity that is human cognition.

/pdf/understanding-and-sharing-intentions-the-origins-of-cultural-4ndpnm3ov3.pdf

Understanding and sharing intentions: The origins of cultural cognition

Re-evaluating Age-Of-Acquisition Effects: Are They Simply Cumulative-Frequency Effects?

The distinctiveness of a face has been found to be an important factor in face recognition. We investigated the effect of the distinctiveness of a face upon subjects' speed and accuracy of recognition following different presentation times and retention intervals. It was found that (1) hits decreased with increasing delay; (2) false alarms increased and d primes decreased with a presentation time of 1 sec compared with 5 sec; (3) distinctive faces received more hits and higher d primes than non-distinctive faces; and (4) response latencies were shorter for distinctive targets than for distinctive distraction or non distinctive targets or distractors. These results were discussed in terms of the literature on the distinctiveness effect in face recognition.

The effects of distinctiveness, presentation time and delay on face recognition

Kutas); "Ethology, Comparative Psychology, and Animal Behavior" (Charles T. Snowdon) "Audition: Some Relations between Normal and Pathological Hearing" (Dennis McFadden and Frederic L. Wightman); "Perception and Representation" (Paul A. Kolers); "Diagnosis and Clinical Assessment: The DSM-III" (H. J. Eysenck, James A. Wakefield, Jr., and Alan F. Friedman); "Personality: Stages, Traits, and the Self" (Jane Loevinger and Elizabeth Knoll); "Evaluation Research: A Methodological Perspective" (Paul M. Wortman); "Instructional Psychology" (Robert M. Gagne and Walter Dick); "Hormonal Influences on Memory" (James L. McGaugh); "Comprehension, Production, and Language Acquisition" (Eve V. Clark and Barbara Frant Hecht); "Animal Cognition" (David Premack); "Cross-cultural Research in Psychology" (Richard W. Brislin); "Psychopathology: Biological Approaches" (Monte S. Buchsbaum and Richard J. Haier); "Personality Structure and Assessments" (Leonard G. Rorer and Thomas A. Widiger); "Social and Personality Development" (Ross D. Parke and Steven R. Asher); "Social Inference" (Reid Hastie); and "Psychology of Adult Development and Aging" (James E. Birren, Walter R. Cunningham, and Koichi Yamamoto). There are author and subject indexes, and cumulative indexes of authors and of chapter titles for volumes 30-34. A detachable order form and envelope lists all annual reviews of all areas and their prices. There is much material in the current volume from the areas of personality and social psychology, and some repetition exists in the several chapters touching on these areas. Perhaps the strongest theme throughout the book is cognitive psychology; it appears in almost all chapters.

Identification evidence : a psychological evaluation

If one takes out what is common to our cases, prosopagnosia is a case of a disorder in the recognition of faces while the perception of them is retained. If the disorder is serious it includes not only human and animal faces but, in an extended sense, every object with an expression and widens out to comprehensive expression agnosia. If this is present, it leads back to a disorder in the sufferer's active capacity for expression. In expression agnosia, as the more serious form, the prosopagnosia is included. In both our cases of prosopagnosia there was also slight object agnosia, stronger simultaneous agnosia, a more or less distinct alexia, in case 2 there was colour agnosia in the form of green-blue disturbance, in case 1 at first there was a complete blindness for colours, out of which colour agnosia developed during the restitution. While the memory (including visual optical memory) for those agnosic disorders was not impaired, it failed completely in prosopagnosia, a difference which seems s...

Hadyn D. Ellis

Papers

Re-evaluating Age-Of-Acquisition Effects: Are They Simply Cumulative-Frequency Effects?

The effects of distinctiveness, presentation time and delay on face recognition

Identification evidence : a psychological evaluation

Bodamer's (1947) paper on prosopagnosia

Photofit constructions versus verbal descriptions of faces.