A network that learns to recognize three-dimensional objects - PubMed (original) (raw)
. 1990 Jan 18;343(6255):263-6.
doi: 10.1038/343263a0.
Affiliations
- PMID: 2300170
- DOI: 10.1038/343263a0
A network that learns to recognize three-dimensional objects
T Poggio et al. Nature. 1990.
Abstract
The visual recognition of three-dimensional (3-D) objects on the basis of their shape poses at least two difficult problems. First, there is the problem of variable illumination, which can be addressed by working with relatively stable features such as intensity edges rather than the raw intensity images. Second, there is the problem of the initially unknown pose of the object relative to the viewer. In one approach to this problem, a hypothesis is first made about the viewpoint, then the appearance of a model object from such a viewpoint is computed and compared with the actual image. Such recognition schemes generally employ 3-D models of objects, but the automatic learning of 3-D models is itself a difficult problem. To address this problem in computational vision, we have developed a scheme, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view. A network equivalent to this scheme will thus 'recognize' the object on which it was trained from any viewpoint.
Comment in
- Artificial intelligence: recognizing three dimensions.
Longuet-Higgins HC. Longuet-Higgins HC. Nature. 1990 Jan 18;343(6255):214-5. doi: 10.1038/343214a0. Nature. 1990. PMID: 2300164 No abstract available.
Similar articles
- 3-D object recognition using 2-D views.
Li W, Bebis G, Bourbakis NG. Li W, et al. IEEE Trans Image Process. 2008 Nov;17(11):2236-55. doi: 10.1109/TIP.2008.2003404. IEEE Trans Image Process. 2008. PMID: 18854254 - Learning to recognize three-dimensional objects.
Roth D, Yang MH, Ahuja N. Roth D, et al. Neural Comput. 2002 May;14(5):1071-103. doi: 10.1162/089976602753633394. Neural Comput. 2002. PMID: 11972908 - Analysis of cluttered scenes using an elastic matching approach for stereo images.
Eckes C, Triesch J, von der Malsburg C. Eckes C, et al. Neural Comput. 2006 Jun;18(6):1441-71. doi: 10.1162/neco.2006.18.6.1441. Neural Comput. 2006. PMID: 16764510 - View-invariant object category learning, recognition, and search: how spatial and object attention are coordinated using surface-based attentional shrouds.
Fazl A, Grossberg S, Mingolla E. Fazl A, et al. Cogn Psychol. 2009 Feb;58(1):1-48. doi: 10.1016/j.cogpsych.2008.05.001. Epub 2008 Jul 23. Cogn Psychol. 2009. PMID: 18653176 Review. - Model-based interpretation of complex and variable images.
Taylor CJ, Cootes TF, Lanitis A, Edwards G, Smyth P, Kotcheff AC. Taylor CJ, et al. Philos Trans R Soc Lond B Biol Sci. 1997 Aug 29;352(1358):1267-74. doi: 10.1098/rstb.1997.0109. Philos Trans R Soc Lond B Biol Sci. 1997. PMID: 9304693 Free PMC article. Review.
Cited by
- How well do rudimentary plasticity rules predict adult visual object learning?
Lee MJ, DiCarlo JJ. Lee MJ, et al. PLoS Comput Biol. 2023 Dec 11;19(12):e1011713. doi: 10.1371/journal.pcbi.1011713. eCollection 2023 Dec. PLoS Comput Biol. 2023. PMID: 38079444 Free PMC article. - Viewpoint dependence and scene context effects generalize to depth rotated three-dimensional objects.
Kallmayer A, Võ ML, Draschkow D. Kallmayer A, et al. J Vis. 2023 Sep 1;23(10):9. doi: 10.1167/jov.23.10.9. J Vis. 2023. PMID: 37707802 Free PMC article. - Macaques recognize features in synthetic images derived from ventral stream neurons.
Mueller KN, Carter MC, Kansupada JA, Ponce CR. Mueller KN, et al. Proc Natl Acad Sci U S A. 2023 Mar 7;120(10):e2213034120. doi: 10.1073/pnas.2213034120. Epub 2023 Mar 1. Proc Natl Acad Sci U S A. 2023. PMID: 36857345 Free PMC article. - Challenging the Classical View: Recognition of Identity and Expression as Integrated Processes.
Schwartz E, O'Nell K, Saxe R, Anzellotti S. Schwartz E, et al. Brain Sci. 2023 Feb 10;13(2):296. doi: 10.3390/brainsci13020296. Brain Sci. 2023. PMID: 36831839 Free PMC article. - Individual differences in classification images of Mooney faces.
Canas-Bajo T, Whitney D. Canas-Bajo T, et al. J Vis. 2022 Dec 1;22(13):3. doi: 10.1167/jov.22.13.3. J Vis. 2022. PMID: 36458961 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources