Abstract
To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character of both natural and artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.
Full Text
The Full Text of this article is available as a PDF (304.7 KB).
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Biederman I., Ju G. Surface versus edge-based determinants of visual recognition. Cogn Psychol. 1988 Jan;20(1):38–64. doi: 10.1016/0010-0285(88)90024-2. [DOI] [PubMed] [Google Scholar]
- Biederman I. Recognition-by-components: a theory of human image understanding. Psychol Rev. 1987 Apr;94(2):115–147. doi: 10.1037/0033-295X.94.2.115. [DOI] [PubMed] [Google Scholar]
- Bülthoff H. H., Edelman S. Psychophysical support for a two-dimensional view interpolation theory of object recognition. Proc Natl Acad Sci U S A. 1992 Jan 1;89(1):60–64. doi: 10.1073/pnas.89.1.60. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Cutzu F., Edelman S. Faithful representation of similarities among three-dimensional shapes in human vision. Proc Natl Acad Sci U S A. 1996 Oct 15;93(21):12046–12050. doi: 10.1073/pnas.93.21.12046. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Edelman S., Duvdevani-Bar S. Similarity, connectionism, and the problem of representation in vision. Neural Comput. 1997 May 15;9(4):701–720. doi: 10.1162/neco.1997.9.4.701. [DOI] [PubMed] [Google Scholar]
- Jolicoeur P., Gluck M. A., Kosslyn S. M. Pictures and names: making the connection. Cogn Psychol. 1984 Apr;16(2):243–275. doi: 10.1016/0010-0285(84)90009-4. [DOI] [PubMed] [Google Scholar]
- Logothetis N. K., Pauls J., Poggio T. Shape representation in the inferior temporal cortex of monkeys. Curr Biol. 1995 May 1;5(5):552–563. doi: 10.1016/s0960-9822(95)00108-4. [DOI] [PubMed] [Google Scholar]
- Marr D., Nishihara H. K. Representation and recognition of the spatial organization of three-dimensional shapes. Proc R Soc Lond B Biol Sci. 1978 Feb 23;200(1140):269–294. doi: 10.1098/rspb.1978.0020. [DOI] [PubMed] [Google Scholar]
- Poggio T., Edelman S. A network that learns to recognize three-dimensional objects. Nature. 1990 Jan 18;343(6255):263–266. doi: 10.1038/343263a0. [DOI] [PubMed] [Google Scholar]
- Poggio T., Girosi F. Regularization algorithms for learning that are equivalent to multilayer networks. Science. 1990 Feb 23;247(4945):978–982. doi: 10.1126/science.247.4945.978. [DOI] [PubMed] [Google Scholar]
- Price C. J., Humphreys G. W. The effects of surface detail on object categorization and naming. Q J Exp Psychol A. 1989 Nov;41(4):797–827. doi: 10.1080/14640748908402394. [DOI] [PubMed] [Google Scholar]
- Shepard R. N. Multidimensional scaling, tree-fitting, and clustering. Science. 1980 Oct 24;210(4468):390–398. doi: 10.1126/science.210.4468.390. [DOI] [PubMed] [Google Scholar]
- Tanaka K. Inferotemporal cortex and higher visual functions. Curr Opin Neurobiol. 1992 Aug;2(4):502–505. doi: 10.1016/0959-4388(92)90187-p. [DOI] [PubMed] [Google Scholar]
- Tanaka K. Inferotemporal cortex and object vision. Annu Rev Neurosci. 1996;19:109–139. doi: 10.1146/annurev.ne.19.030196.000545. [DOI] [PubMed] [Google Scholar]
- Ullman S. Aligning pictorial descriptions: an approach to object recognition. Cognition. 1989 Aug;32(3):193–254. doi: 10.1016/0010-0277(89)90036-x. [DOI] [PubMed] [Google Scholar]
- Wang G., Tanaka K., Tanifuji M. Optical imaging of functional organization in the monkey inferotemporal cortex. Science. 1996 Jun 14;272(5268):1665–1668. doi: 10.1126/science.272.5268.1665. [DOI] [PubMed] [Google Scholar]