Abstract
Humans have the ability to identify objects under varying lighting conditions with extraordinary accuracy. We investigated the behavioral aspects of this ability and compared it to the performance of the illumination cones (IC) model of Belhumeur and Kriegman [1998]. In five experiments, observers learned 10 faces under a small subset of illumination directions. We then tested observers' recognition ability under different illuminations. Across all experiments, recognition performance was found to be dependent on the distance between the trained and tested illumination directions. This effect was modulated by the nature of the trained illumination directions. Generalizations from frontal illuminations were different than generalizations from extreme illuminations. Similarly, the IC model was also sensitive to whether the trained images were near-frontal or extreme. Thus, we find that the nature of the images in the training set affects the accuracy of an object's representation under variable lighting for both humans and the model. Beyond this general correspondence, the microstructure of the generalization patterns for both humans and the IC model were remarkably similar, suggesting that the two systems may employ related algorithms.
- Atick, J. J., Griffin, P. A., and Redlich, A. N. 1996. Statistical approach to shape from shading: Reconstruction of three-dimensional face surfaces from single two-dimensional images. Neural Computation 8, 6, 1321--1340.]] Google ScholarDigital Library
- Belhumeur, P. N. and Kriegman, D. J. 1998. What is the set of images of an object under all possible illumination conditions? Int. J. Comput. Vision 28, 3, 245--260.]] Google ScholarDigital Library
- Belhumeur, P. N., Hespanha, J. P., and Kriegman, D. J. 1997. Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19, 7, 711--720.]] Google ScholarDigital Library
- Biederman, I. 1987. Recognition-by-components: A theory of human image understanding. Psychological Review 94, 2, 115--147.]]Google ScholarCross Ref
- Biederman, I. and Gerhardstein, P. C. 1993. Recognizing depth-rotated objects: Evidence and conditions for three-dimensional viewpoint invariance. Journal of Experimental Psychology: Human Perception and Performance 19, 6, 1162--1182.]]Google ScholarCross Ref
- Binford, T. O. 1971. Visual perception by computer. In IEEE Conference on Systems and Control. Miami, FL.]]Google Scholar
- Braje, W. L. 2003. Illumination encoding in face recognition: Effect of position shift. Journal of Vision 3, 2, 161--170.]]Google ScholarCross Ref
- Braje, W. L., Kersten, D., Tarr, M. J., and Troje, N. F. 1998. Illumination effects in face recognition. Psychobiology 26, 4 (Aug.), 371--380.]]Google Scholar
- Braje, W. L., Legge, G. E., and Kersten, D. 2000. Invariant recognition of natural objects in the presence of shadows. Perception 29, 4, 383--398.]]Google ScholarCross Ref
- Fukushima, K. 2000. Active and adaptive vision: Neural network models. In Biologically Motivated Computer Vision, S.-W. Lee, H. H. Bülthoff, and T. Poggio, Eds. Vol. 1811. Springer-Verlag, New York. 623--634.]] Google ScholarDigital Library
- Georghiades, A. S., Kriegman, D. J., and Belhumeur, P. N. 1998. Illumination cones for recognition under variable lighting: Faces. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog. 52--59.]] Google ScholarDigital Library
- Georghiades, A. S., Belhumeur, P. N., and Kriegman, D. J. 2001. From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intell. 23, 6 (June), 643--660.]] Google ScholarDigital Library
- Gross, R., Baker, S., Matthews, I., and Kanade, T. 2004. Face recognition across pose and illumination. In Handbook of Face Recognition, S. Z. Li and A. K. Jain, Eds. Springer-Verlag, New York.]]Google Scholar
- Hallinan, P. W. 1994. A low-dimensional representation of human faces for arbitrary lighting conditions. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog. 995--999.]]Google ScholarCross Ref
- Hallinan, P. W., Gordon, G., Yuille, A. L., Giblin, P., and Mumford, D. 1999. Two- and Three-Dimensional Patterns of the Face. A.K. Peters, Natick, MA.]] Google ScholarDigital Library
- Hayward, W. G. and Tarr, M. J. 1997. Testing conditions for viewpoint invariance in object recognition. Journal of Experimental Psychology: Human Perception and Performance 23, 5 (Oct.), 1511--1521.]]Google ScholarCross Ref
- Horn, B. K. P. 1975. Obtaining Shape from Shading Information. McGraw-Hill, New York.]]Google Scholar
- Johnston, A., Hill, H., and Carman, N. 1992. Recognizing faces: Effects of lighting direction, inversion, and brightness reversal. Perception 21, 3, 365--375.]]Google ScholarCross Ref
- Kardos, L. 1934. Ding und Schatten. Zeitschrift für Psychologie 23.]]Google Scholar
- Kersten, D., Knill, D. C., Mamassian, P., and Bülthoff, I. 1996. Illusory motion from shadows. Nature (London) 379, 31.]]Google ScholarCross Ref
- Kersten, D., Mamassian, P., and Knill, D. C. 1997. Moving cast shadows induce apparent motion in depth. Perception 26, 2, 171--192.]]Google ScholarCross Ref
- Kersten, D., Mamassian, P., and Yuille, A. 2004. Object perception as Bayesian inference. Annual Review of Psychology 55, 271--304.]]Google ScholarCross Ref
- Lades, M., Vorbrüggen, J. C., Buhmann, J., Lange, J., von der Malsburg, C., Würtz, R. P., and Konen, W. 1993. Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers 42, 300--311.]] Google ScholarDigital Library
- Logothetis, N. K. and Pauls, J. 1995. Psychophysical and physiological evidence for viewer-centered object representation in the primate. Cerebral Cortex 5, 3, 270--288.]]Google ScholarCross Ref
- Lowe, D. G. 2000. Towards a computational model for object recognition in IT cortex. In Biologically Motivated Computer Vision, S.-W. Lee, H. H. Bülthoff, and T. Poggio, Eds. Vol. 1811. Springer-Verlag, New York, 20--31.]] Google ScholarDigital Library
- Marr, D. 1982. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. Freeman, San Francisco, CA.]] Google ScholarDigital Library
- Marr, D. and Nishihara, H. K. 1978. Representation and recognition of the spatial organization of three-dimensional shapes. In Proc. R. Soc. of Lond. B, 200. 269--294.]]Google ScholarCross Ref
- Moore, C. and Cavanagh, P. 1998. Recovery of 3D volume from 2-tone images of novel objects. Cognition 67, 1-2 (July), 45--71.]] Google ScholarDigital Library
- Moses, Y., Adini, Y., and Ullman, S. 1994. Face recognition: The problem of compensating for changes in illumination direction. In Computer Vision - ECCV '94, J.-O. Eklundh, Ed. Lecture Notes in Computer Science, vol. 800. Springer-Verlag, New York, 286--296.]] Google ScholarDigital Library
- Moses, Y., Ullman, S., and Edelman, S. 1996. Generalization to novel images in upright and inverted faces. Perception 25, 443--462.]]Google ScholarCross Ref
- Ramachandran, V. S. 1988. Perception of shape from shading. Nature (London) 331, 14, 163--166.]]Google ScholarCross Ref
- Riesenhuber, M. and Poggio, T. 2000. CBF: A new framework for object categorization in cortex. In Biologically Motivated Computer Vision, S.-W. Lee, H. H. Bülthoff, and T. Poggio, Eds. Vol. 1811. Springer-Verlag, New York. 1--9.]] Google ScholarDigital Library
- Sanocki, T., Bowyer, K. W., Heath, M. D., and Sarkar, S. 1998. Are edges sufficient for object recognition? Journal of Experimental Psychology: Human Perception and Performance 24, 1, 340--349.]]Google ScholarCross Ref
- Tarr, M. J. 1995. Rotating objects to recognize them: A case study of the role of viewpoint dependency in the recognition of three-dimensional objects. Psychonomic Bulletin and Review 2, 1, 55--82.]]Google ScholarCross Ref
- Tarr, M. J. and Gauthier, I. 1998. Do viewpoint-dependent mechanisms generalize across members of a class? Cognition 67, 1-2 (July), 71--108.]]Google Scholar
- Tarr, M. J., Kersten, D., and Bülthoff, H. H. 1998a. Why the visual system might encode the effects of illumination. Vision Research 38, 15--16 (Aug.), 2259--2275.]]Google ScholarCross Ref
- Tarr, M. J., Williams, P., Hayward, W. G., and Gauthier, I. 1998b. Three-dimensional object recognition is viewpoint-dependent. Nature Neuroscience 1, 4 (Aug.), 275--277.]]Google ScholarCross Ref
- Turk, M. and Pentland, A. 1991a. Eigenfaces for recognition. Journal of Cognitive Neuroscience 3, 1, 71--86.]] Google ScholarDigital Library
- Turk, M. and Pentland, A. 1991b. Face recognition using eigenfaces. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog. 586--591.]]Google Scholar
- Ullman, S. and Sali, E. 2000. Object classification using a fragment-based representation. In Biologically Motivated Computer Vision, S.-W. Lee, H. H. Bülthoff, and T. Poggio, Eds. Vol. 1811. Springer-Verlag, New York. 73--87.]] Google ScholarDigital Library
- Ullman, S., Vidal-Naquet, M., and Sali, E. 2002. Visual features of intermediate complexity and their use in classification. Nature Neuroscience 5, 682--687.]]Google ScholarCross Ref
- Vuong, Q. C., Peissig, J. J., Harrison, M. C., and Tarr, M. J. 2005. The role of surface pigmentation for recognition revealed by contrast reversal in faces and greebles. Vision Research 45, 10, 1213--1223.]]Google ScholarCross Ref
- Williams, P. and Tarr, M. J. 2001. RSVP: Experimental control software for MacOS {online}.]]Google Scholar
- Zhang, L. and Samaras, D. 2006. Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics. IEEE Trans. Pattern Anal. Mach. Intell. 28, 3 (Mar.), 351--363.]] Google ScholarDigital Library
- Zhou, S. K. and Chellappa, R. 2005. Image-based face recognition under illumination and pose variations. Journal of the Optical Society of America A 22, 217--229.]]Google ScholarCross Ref
- Zhou, S. K., Aggarwal, G., Chellappa, R., and Jacobs, D. W. 2007. Appearance characterization of linear lambertian objects, generalized photometric stereo, and illumination-invariant face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 29, 2 (Feb.), 230--245.]] Google ScholarDigital Library
Index Terms
- Identifying faces across variations in lighting: Psychophysics and computation
Recommendations
An improved face recognition technique based on modular PCA approach
A face recognition algorithm based on modular PCA approach is presented in this paper. The proposed algorithm when compared with conventional PCA algorithm has an improved recognition rate for face images with large variations in lighting direction and ...
Detecting Faces in Images: A Survey
Images containing faces are essential to intelligent vision-based human computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation, and expression recognition. However, many reported methods ...
Face recognition under arbitrary illumination using illuminated exemplars
Recently, the importance of face recognition has been increasingly emphasized since popular CCD cameras are distributed to various applications. However, facial images are dramatically changed by lighting variations, so that facial appearance changes ...
Comments