Aligning pictorial descriptions: an approach to object recognition - PubMed (original) (raw)
Aligning pictorial descriptions: an approach to object recognition
S Ullman. Cognition. 1989 Aug.
Abstract
This paper examines the problem of shape-based object recognition, and proposes a new approach, the alignment of pictorial descriptions. The first part of the paper reviews general approaches to visual object recognition, and divides these approaches into three broad classes: invariant properties methods, object decomposition methods, and alignment methods. The second part presents the alignment method. In this approach the recognition process is divided into two stages. The first determines the transformation in space that is necessary to bring the viewed object into alignment with possible object models. This stage can proceed on the basis of minimal information, such as the object's dominant orientation, or a small number of corresponding feature points in the object and model. The second stage determines the model that best matches the viewed object. At this stage, the search is over all the possible object models, but not over their possible views, since the transformation has already been determined uniquely in the alignment stage. The proposed alignment method also uses abstract description, but unlike structural description methods it uses them pictorially, rather than in symbolic structural descriptions.
Similar articles
- View-dependent object recognition by monkeys.
Logothetis NK, Pauls J, Bülthoff HH, Poggio T. Logothetis NK, et al. Curr Biol. 1994 May 1;4(5):401-14. doi: 10.1016/s0960-9822(00)00089-0. Curr Biol. 1994. PMID: 7922354 - The configural advantage in object change detection persists across depth rotation.
Favelle SK, Hayward WG, Burke D, Palmisano S. Favelle SK, et al. Percept Psychophys. 2006 Nov;68(8):1254-63. doi: 10.3758/bf03193725. Percept Psychophys. 2006. PMID: 17378412 - Object recognition without knowledge of object orientation.
Turnbull OH, Laws KR, McCarthy RA. Turnbull OH, et al. Cortex. 1995 Jun;31(2):387-95. doi: 10.1016/s0010-9452(13)80371-1. Cortex. 1995. PMID: 7555015 - 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. - Differing approaches to two-dimensional shape recognition.
Quinlan PT. Quinlan PT. Psychol Bull. 1991 Mar;109(2):224-41. doi: 10.1037/0033-2909.109.2.224. Psychol Bull. 1991. PMID: 2034751 Review.
Cited by
- Interpreting the orientation of objects: A cross-disciplinary review.
Harris IM. Harris IM. Psychon Bull Rev. 2024 Aug;31(4):1503-1515. doi: 10.3758/s13423-024-02458-8. Epub 2024 Feb 1. Psychon Bull Rev. 2024. PMID: 38302790 Free PMC article. Review. - Modal and amodal cognition: an overarching principle in various domains of psychology.
Kaup B, Ulrich R, Bausenhart KM, Bryce D, Butz MV, Dignath D, Dudschig C, Franz VH, Friedrich C, Gawrilow C, Heller J, Huff M, Hütter M, Janczyk M, Leuthold H, Mallot H, Nürk HC, Ramscar M, Said N, Svaldi J, Wong HY. Kaup B, et al. Psychol Res. 2024 Mar;88(2):307-337. doi: 10.1007/s00426-023-01878-w. Epub 2023 Oct 17. Psychol Res. 2024. PMID: 37847268 Free PMC article. Review. - Perceptual similarity judgments do not predict the distribution of errors in working memory.
Tomić I, Bays PM. Tomić I, et al. J Exp Psychol Learn Mem Cogn. 2024 Apr;50(4):535-549. doi: 10.1037/xlm0001172. Epub 2022 Nov 28. J Exp Psychol Learn Mem Cogn. 2024. PMID: 36442045 Free PMC article. - Three-dimensional pose discrimination in natural images of humans.
Zhu H, Yuille A, Kersten D. Zhu H, et al. Cogsci. 2021 Jul;43:223-229. Cogsci. 2021. PMID: 35969705 Free PMC article. - Use of superordinate labels yields more robust and human-like visual representations in convolutional neural networks.
Ahn S, Zelinsky GJ, Lupyan G. Ahn S, et al. J Vis. 2021 Dec 1;21(13):13. doi: 10.1167/jov.21.13.13. J Vis. 2021. PMID: 34967860 Free PMC article.
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources