Testing principal component representations for faces

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Hancock, P.J.B., Bruce, V., Burton, A.M. (1997). Testing principal component representations for faces. In Bullinaria, J.A., Glasspool, D.W., Houghton, G., eds.: 4th Neural Computation and Psychology Workshop. Springer. London, 84–97.




A variety of experimental results indicate that the human visual system processes faces at least to some extent holistically, rather than by analysing individual features such as nose and eyes. Principal Components Analysis (PCA) of face images, which is widely used in engineering approaches to face identification, produces an inherently global representation. We investigate the psychological plausibility of this representation, looking at correlations with human perceptions of memorability and similarity. We show that transformation of faces to an average shape prior to PCA improves correlations with human ratings

Extended Abstract


Used References

Baddeley RJ and Hancock PJB, A statistical analysis of natural images matches psychophysically derived orientation tuning curves. Proceedings of the Royal Society B 1991, 246: 219–223 http://dx.doi.org/10.1098/rspb.1991.0147

Bartlett MS and Sejnowski TJ, Independent component analysis of face images: a representation for face recognition. Proceedings of the 4th Annual Joint Symposium on Neural Computation, Pasadena, CA. La Jolla, CA: Institute for Neural Computation 1997.

Biederman, I, Neural and psychophysical analysis of object and face recognition, Talk at NATO ASI: Face recognition, from theory to application, Stirling, July 1997.

Bruce V, Hanna E, Dench N, Healy P and Burton AM, The importance of ‘mass’ in line drawings of faces, Applied Cognitive Psychology 1992, 6: 619628

Craw I and Cameron P, Parameterising images for recognition and reconstruction In Mowforth P, editor, Proceedings of the British Machine Vision Conference, London: Springer Verlag, 1991 pages 367–370

Dakin SC, The visual representation of texture, PhD thesis, Department of Psychology, University of Stirling, 1994.

Galper RE and Hochberg J, Repetition memory for photographs of faces, American Journal of Psychology 1971, 84: 351–354 http://dx.doi.org/10.2307/1420466

Hancock PJB, Bruce V and Burton AM, A comparison of two computer-based face identification systems with human perceptions of faces, Submitted to Vision Research 1997.

Hancock PJB, Burton AM, and Bruce V, Face processing: human perception and principal components analysis, Memory and Cognition 1996, 24: 26–40 http://dx.doi.org/10.3758/BF03197270

Lades M, Vorbrûggen JC, Buhman J, Lage J, von der Malsburg C, Wûrtz RP and Konen W, Distortion invariant object recognition in the dynamic link architecture, IEEE Transactions on Computers 1993, 42: 300–311 http://dx.doi.org/10.1109/12.210173

Moses Y, Adini Y and Ullman S, Face recognition: the problem of compensating for changes in illumination direction, Proceedings of ECCV-94, Stockholm, 2–6 May 1994, Berlin: Springer-Verlag, 1994, pages 286–296.

Sanger TD, Optimal unsupervised learning in a single-layer linear feedforward neural network, Neural Networks 1989, 2: 459–473 http://dx.doi.org/10.1016/0893-6080(89)90044-0

Thompson P, Magaret Thatcher: A new illusion, Perception 1980, 9:483— 484

Turk M and Pentland A, Eigenfaces for recognition, Journal of Cognitive Neuroscience 1991 3: 71–86 http://dx.doi.org/10.1162/jocn.1991.3.1.71

Vokey JR and Read JD, Familiarity, memorability and the effect of typicality on the recognition of faces. Memory and Cognition 1992, 20: 291–302 http://dx.doi.org/10.3758/BF03199666

Watt RJ, A computational examination of image segmentation and the initial stages of human vision, Perception 1994, 23: 383–398 http://dx.doi.org/10.1068/p230383


Full Text


intern file

Sonstige Links