Object perception as Bayesian inference. Kersten, D, Mamassian, P, & Yuille, A Annu Rev Psychol, 55:271–304, 2004. abstract bibtex We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.
@article{kersten_object_2004,
title = {Object perception as {Bayesian} inference},
volume = {55},
abstract = {We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.},
journal = {Annu Rev Psychol},
author = {Kersten, D and Mamassian, P and Yuille, A},
year = {2004},
pmid = {14744217},
keywords = {*Bayes Theorem, *Decision Making, *Learning, *Psychological Theory, Humans, Psychophysics, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, P.H.S., Visual Perception/*physiology},
pages = {271--304},
}
Downloads: 0
{"_id":"HEC7YsZgJQBTPF7pF","bibbaseid":"kersten-mamassian-yuille-objectperceptionasbayesianinference-2004","downloads":0,"creationDate":"2015-02-08T05:14:47.878Z","title":"Object perception as Bayesian inference","author_short":["Kersten, D","Mamassian, P","Yuille, A"],"year":2004,"bibtype":"article","biburl":"https://bibbase.org/zotero/michaeltarr","bibdata":{"bibtype":"article","type":"article","title":"Object perception as Bayesian inference","volume":"55","abstract":"We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.","journal":"Annu Rev Psychol","author":[{"propositions":[],"lastnames":["Kersten"],"firstnames":["D"],"suffixes":[]},{"propositions":[],"lastnames":["Mamassian"],"firstnames":["P"],"suffixes":[]},{"propositions":[],"lastnames":["Yuille"],"firstnames":["A"],"suffixes":[]}],"year":"2004","pmid":"14744217","keywords":"*Bayes Theorem, *Decision Making, *Learning, *Psychological Theory, Humans, Psychophysics, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, P.H.S., Visual Perception/*physiology","pages":"271–304","bibtex":"@article{kersten_object_2004,\n\ttitle = {Object perception as {Bayesian} inference},\n\tvolume = {55},\n\tabstract = {We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.},\n\tjournal = {Annu Rev Psychol},\n\tauthor = {Kersten, D and Mamassian, P and Yuille, A},\n\tyear = {2004},\n\tpmid = {14744217},\n\tkeywords = {*Bayes Theorem, *Decision Making, *Learning, *Psychological Theory, Humans, Psychophysics, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, P.H.S., Visual Perception/*physiology},\n\tpages = {271--304},\n}\n\n","author_short":["Kersten, D","Mamassian, P","Yuille, A"],"key":"kersten_object_2004","id":"kersten_object_2004","bibbaseid":"kersten-mamassian-yuille-objectperceptionasbayesianinference-2004","role":"author","urls":{},"keyword":["*Bayes Theorem","*Decision Making","*Learning","*Psychological Theory","Humans","Psychophysics","Research Support","Non-U.S. Gov't","Research Support","U.S. Gov't","P.H.S.","Visual Perception/*physiology"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"search_terms":["object","perception","bayesian","inference","kersten","mamassian","yuille"],"keywords":["*bayes theorem","*decision making","*learning","*psychological theory","humans","psychophysics","research support","non-u.s. gov't","research support","u.s. gov't","p.h.s.","visual perception/*physiology"],"authorIDs":[],"dataSources":["hEoKh4ygEAWbAZ5iy","MDN92uztrK9rBiHJj","5qXSH7BrePnXHtcrf"]}