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

Newborns' preferential tracking of face-like stimuli and its subsequent decline☆

Three experiments are reported in which recognition of faces from whole faces or internal or external features was compared. In the first experiment, where the faces were of famous people, an advantage was found for identification from internal features. In the second experiment involving unfamiliar faces, however, no difference was found in recognition rates when subjects were given the internal or the external features. In a third experiment famous faces were presented and mixed with other famous faces for a recognition test. As in experiment 1, better recognition occurred from internals as compared with external features. It is argued that the internal representation for familiar faces may be qualitatively different from that for face seen just once. In particular some advantage in feature saliency may accrue to the internal or 'expressive' features of familiar faces. The implications of these results are considered in relation to general theories of face perception and recognition.

Identification of familiar and unfamiliar faces from internal and external features: Some implications for theories of face recognition.

1. Introduction.- to aspects of face processing: Ten questions in need of answers.- 2. Perceptual Processes.- Microgenesis of face perception..- Recognition memory transfer between spatial- frequency analyzed faces..- Reaction time measures of feature saliency in a perceptual integration task..- Perception of upside-down faces: An analysis from the viewpoint of cue-saliency..- 3. Memory Processes.- On the memorability of the human face..- Face recognition is not unique. Evidence from individual differences..- Lateral reversal and facial recognition memory: Are right-lookers special?.- Context effects in recognition memory of faces: Some theoretical problems..- 4. Cognitive Processes.- Recognising familiar faces..- Face recognition: More than a feeling of familiarity?.- Getting semantic information from familiar faces..- What happens when a face rings a bell?: The automatic processing of famous faces..- 5. Socio-Cognitive Factors.- Levels of representation and memory for faces..- Formation of facial prototypes..- Stereotyping and face memory..- The influence of race on face recognition..- Faces, prototypes, and additive tree representations..- 6. Cortical Specialisation.- Functional organization of visual neurones processing face identity..- Hemispheric asymmetry in face processing in infancy..- Models of laterality effects in face perception..- Hemispheric asymmetries in face recognition and naming: effects of prior stimulus exposure..- Patterns of cerebral dominance in wholistic and featural stages of facial processing..- Hemispheric differences in the evoked potential to face stimuli..- Cerebral and behavioural asymmetries in the processing of "unusual" faces: A review..- 7. Prosopagnosias.- Current issues on prosopagnosia..- The cognitive psychophysiology of prosopagnosia..- Prosopagnosia: Anatomic and physiologic aspects..- Faces and non-faces in prosopagnosic patients..- Observations on a case of prosopagnosia..- 8. Brain Pathology.- Facial processing in the dementias..- The matching of famous and unknown faces, given either the internal or the external features: A study on patients with unilateral brain lesions..- Face recognition dysfunction and delusional mis identification syndromes (D.M.S.)..- 9. Facial Expressions.- Facial expression processing..- The perception of action versus feeling in facial expression..- Towards the quantification of facial expressions with the use of a mathematic model of the face..- Is the faster processing of expressions of happiness modality-specific?.- Primary stages in single-glance face recognition: Expression and identity..- Affective and cognitive decisions on faces in normals..- 10. Applications and Computer Technology.- Dynamics of facial recall..- The recall and reconstruction of faces: Implications for theory and practice..- An interactive computer system for retrieving faces..- Investigating face recognition with an image processing computer..- Practical face recognition and verification with WISARD..- 11. An Overview.- Plenary session. An overview. Complementary approaches to common problems in face recognition..- 12. References.- Addresses of Principal Authors.

Aspects of face processing

Accounts of the major DMSs are given using theoretical models of the functional components underlying recognition of familiar people. Thus, Capgras' syndrome is suggested to involve impairment of processes that can support 'covert' recognition of familiar faces in prosopagnosia. It therefore forms a potential 'mirror image' of the impairments underlying prosopagnosia, and earlier attempts to link the two conditions directly are questioned. Fr√©goli syndrome and intermetamorphosis are explained as defects at different stages of an information-processing chain. Not only are these accounts consistent with the association of different DMSs with different brain injuries, but they also offer both suggestions for new inquiries and predictions about possible preserved and impaired abilities.

Hadyn D. Ellis

Papers

Newborns' preferential tracking of face-like stimuli and its subsequent decline☆

Identification of familiar and unfamiliar faces from internal and external features: Some implications for theories of face recognition.

Aspects of face processing

Accounting for delusional misidentifications.

Perceiving and remembering faces