How Should We RepresentFaces for Automatic Recognition?
August 1999 (vol. 21 no. 8)
pp. 725-736
DOI Bookmark:
http://doi.ieeecomputersociety.org/10.1109/34.784286
Abstract—We describe results obtained from a testbed used to investigate different codings for automatic face recognition. An eigenface coding of shape-free faces using manually located landmarks was more effective than the corresponding coding of correctly shaped faces. Configuration also proved an effective method of recognition, with rankings given to incorrect matches relatively uncorrelated with those from shape-free faces. Both sets of information combine to improve significantly the performance of either system. The addition of a system, which directly correlated the intensity values of shape-free images, also significantly increased recognition, suggesting extra information was still available. The recognition advantage for shape-free faces reflected and depended upon high-quality representation of the natural facial variation via a disjoint ensemble of shape-free faces; if the ensemble was comprised of nonfaces, a shape-free [1] R.J. Baddeley and P.J.B. Hancock, “A Statistical Analysis of Natural Images Matches Psychophysically Derived Orientation Tuning Curves,” Proc. Royal Soc. B, vol. 246, pp. 219–223, Dec. 1991.[2] P.J. Benson, “Perception and Recognition of Computer-Enhanced Facial Attributes and Abstracted Prototypes,” PhD thesis, Dept.ment of Psychlogy, Univ. of St. Andrews, 1992.[3] P.J. Benson and D.I. Perrett, “Visual Processing of Facial Distinctiveness,” Perception, vol. 23, pp. 75–93, 1994.[4] R. Brunelli and T. Poggio, “Caricatural Effects in Automated Face Perception,” Biological Cybernetics, vol. 69, pp. 235–241, 1993.[5] R. Brunelli and T. Poggio, "Face Recognition: Features vs. Templates," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 1,042-1,053, Oct. 1993.[6] C.-Seok Choi, T. Okazaki, H. Harashima, and T. Takebe, “Basis Generation and Description of Facial Images Using Principal Component Analysis,” Technical Report of IPSJ:Graphics&CAD, vol. 46, pp. 43–50, 1990. available in Japanese.[7] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham, "Active Shape Models—Their Training and Application," Computer Vision and Image Understanding, vol. 61, no. 1, pp. 38-59, Jan. 1995.[8] N.P. Costen, I.G. Craw, G.J. Robertson, and S. Akamatsu, “Automatic Face Recognition: What Representation?” Proc. of European Conf. Vision ECCV'96, vol. l,B. Buxton and R. Cipolla, eds. pp. 504–513, 1996.[9] P. Costen, M. Parker, and I. Craw, “Spatial Content and Spatial Quantisation Effects in Face Recognition,” Perception, vol. 23, pp. 129–146, 1994.[10] I.G. Craw, “A Manifold Model of Face and Object Recognition,” Cognitive and Computational Aspects of Face Recognition, T.R. Valentine, ed. chapter 9, pp. 183–203, London: Routledge, 1995.[11] I. Craw and P. Cameron, “Face Recognition by Computer,” British Machine Vision Conf., pp. 498–507, 1992.[12] K.A. Deffenbacher, D.P. Huff, C. Hendrickson, A. O'Toole, and H. Abdi, “Manipulating Face Gender: Effects on Categorization and Recognition Judgements,” presented at Psychomics, 1995.[13] S. Edelman, D. Reisfeld, and Y. Yeshurun, “Learning to Recognize Faces from Examples,” Lecture Notes in Computer Science, Vol. 588, 1992, pp. 787-791.[14] P.J.B. Hancock, R.J. Baddeley, and L.S. Smith, “Principal Components of Natural Images,” Network, vol. 3, pp. 61–70, Feb. 1992.[15] P.J.B. Hancock, M.A. Burton, and V. Bruce, “Face Processing: Human Perception and Principal Components Analysis,” Memory and Cognition, vol. 24, no. 1, pp. 26–40, Jan. 1996.[16] M. Kirby and L. Sirovich,“Application of Karhunen-Loève procedure for the characterization of human faces,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 103-108, Jan. 1990.[17] T. Kohonen, E. Oja, and P. Lehtiö, “Storage and Processing of Information in Distributed Associative Memory Systems,” Parallel Models of Associative Memory, G. Hinton and J. Anderson, eds. chapter 4, Hillsdale, N.J.: Erlbaum, 1981.[18] M. Lades, J.C. Vorbruggen, J. Buhmann, J. Lange, C. von der Malsburg, R.P. Wurtz, and W. Konen, “Distortion Invariant Object Recognition in the Dynamic Link Architecture,” IEEE Trans. Computers, vol. 42, no. 3, pp. 300-311, Mar. 1993.[19] A. Lanitis, C.J. Taylor, and T.F. Cootes, “An Automatic Face Identification System Using Flexible Appearance Models,” British Machine Vision Conf., pp. 65–74, 1994.[20] K.J. Lee and D. Perrett, “Presentation Time Measures of the Effects of Manipulations in Color Space on Discrimination of Famous Faces,” submitted to Perception, Dec. 1996.[21] M.B. Lewis, “The Spitting Image of an Exemplar-Based Model of Face Recognition,” paper presented to the Experimental Psychology Soc., Apr. 1996.[22] A.J. O'Toole, H. Abdi, K.A. Deffenbacher, and D. Valentin, “Low-Dimensional Representation of Faces in Higher Dimensions of the Face Space,” J. Optical Soc. Am., vol. 10, no. 3, pp. 405–411, Mar. 1993.[23] A.J. O'Toole, K.A. Deffenbacher, H. Abdi, and J.C. Bartlett, “Simulating the“Other-Race Effect,”as a Problem in Perceptual Learning,” Connection Science, vol. 3, no. 2, pp. 163–178, 1991.[24] A.J. O'Toole, K.A. Deffenbacher, Dominique V., and H. Abdi, “Structural Aspects of Face Recognition and the Other Race Effect,” Memory and Cognition, vol. 22, no. 2, pp. 208–224, 1994.[25] A. Pentland, B. Moghaddam, and Starner, "View-Based and Modular Eigenspaces for Face Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1994, pp. 84-91.[26] R.P.N. Rao and D.H. Ballard, “Natural Basis Functions and Topographic Memory for Face Recognition,” Proc. of Int'l Joint Conf. Artificial Intelligence, pp. 10–17, 1995.[27] G. Rhodes, S.E. Brennan, and S. Carey, “Identification and Ratings of Caricatures: Implications for Mental Representations of Faces,” Cognitive Psychology, vol. 19, 473–497, 1987.[28] G. Rhodes and I.G. McLean, “Distinctiveness and Expertise Effects with Homogeneous Stimuli: Towards a Model of Configural Coding,” Perception, vol. 19, pp. 773–794, 1990.[29] G. Rhodes, S. Brake, K. Taylor, and S. Tan, “Expertise and Configural Coding in Face Recognition,” British J. Psychology, vol. 80, no. 3, pp. 313–331, Aug. 1989.[30] G. Robertson and I. Craw, “Testing Face Recognition Systems,” Image and Vision Computing, vol. 12, pp. 609–614, 1994.[31] M.H. Graham,“Issues in real-time data management,” J. Real-Time Systems, vol. 4, pp. 185-202, 1992.[32] M. Turk and A. Pentland, “Eigenfaces for Recognition,” J. Cognitive Neuroscience, vol. 3, pp. 71–86, 1991.[33] S. Ullman, “Aligning Pictorial Descriptions: An Approach to Object Recognition,” Cognition, vol. 32, pp. 193–254, 1989.[34] T. Valentine, “A Unified Account of the Effects of Distinctiveness, Inversion and Race in Face Recognition,” Quarterly J. Experimental Psychology, vol. 43A, pp. 161–204, 1991.[35] T. Vetter and T. Poggio, “Image Synthesis from a Single Example View,” Proc. European Conf. Computer Vision, 1996.[36] J.R. Vokey and J.D. Read, “Familiarity, Memorability, and the Effect of Typicality on the Recognition of Faces,” Memory and Cognition, vol. 20, no. 3, pp. 291–302, 1992.[37] R. Watt, “A Computational Examination of Image Segmentation and the Initial Stages of Human Vision,” Perception, vol. 23, pp. 383–398, 1994.
Index Terms:
Automatic face recognition, eigenfaces, face shape, shape-free faces, caricaturing, face manifold.
Citation:
Ian Craw, Nicholas Costen, Takashi Kato, Shigeru Akamatsu, "How Should We RepresentFaces for Automatic Recognition?," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 8, pp. 725-736, Aug. 1999, doi:10.1109/34.784286
Usage of this product signifies your acceptance of the
Terms of Use.
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb