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

A cognitive neuroscience of belief

Ear asymmetry for the perception of monaurally presented words accompanied by binaural white noise

The question of whether age-of-acquisition (AoA), frequency, and repetition priming effects occur at a common stage or at different stages of processing is addressed. Two single-stage accounts (i.e., cumulative frequency and a neural-network simulation) are considered in regard to their predictions concerning the interactions between AoA and frequency with aging and priming effects. A repetition-priming face-classification task was conducted on both older and younger participants to test these predictions. Consistent with the predictions of the neural-network simulation, AoA had an effect on reaction times that could not be explained by cumulative frequency alone. Also, as predicted by the simulation, the size of the priming effect was determined by the cumulative frequency of the item. It is discussed how this evidence is supportive of the notion that AoA, frequency, and priming all have effects at a common and single stage during face processing.

/pdf/exploring-a-neural-network-account-of-age-of-acquisition-11wb18lvbf.pdf

Exploring a neural-network account of age-of-acquisition effects using repetition priming of faces.

Relative suppression of magical thinking: a transcranial magnetic stimulation study.

Three experiments are reported which explore the effects of lines on faces upon recognition memory. In Expt I a comparison of recognition memory for photographs of real faces with memory for Photofit faces indicated that memory for the former is significantly better. Experiment II examined one possible explanation for the first results by comparing memory for faces with memory for the same faces containing lines representing the feature boundaries of Photofit faces. The unlined faces were recognized more readily. This result was replicated in Expt III which also indicated that random lines produced the same deleterious effect on face memory as the systematic Photofit-type lines.

The practical and theoretical implications of these results are discussed in relation to forensic face recall systems and pattern recognition.

Hadyn D. Ellis

Papers

A cognitive neuroscience of belief

Ear asymmetry for the perception of monaurally presented words accompanied by binaural white noise

Exploring a neural-network account of age-of-acquisition effects using repetition priming of faces.

Relative suppression of magical thinking: a transcranial magnetic stimulation study.

Remembering pictures of real and unreal faces: Some practical and theoretical considerations.