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.
Description
Object perception as Bayesian inference. [Annu Rev Psychol. 2004] - PubMed Result
%0 Journal Article
%1 KerstenEtAl2004
%A Kersten, Daniel
%A Mamassian, Pasal
%A Yuille, Alan
%D 2004
%J Annu Rev Psychol
%K bayesianinference perception vision
%P 271-304
%R 10.1146/annurev.psych.55.090902.142005
%T Object perception as Bayesian inference
%U http://www.ncbi.nlm.nih.gov/pubmed/14744217
%V 55
%X 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{KerstenEtAl2004,
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.},
added-at = {2009-06-13T13:03:49.000+0200},
author = {Kersten, Daniel and Mamassian, Pasal and Yuille, Alan},
biburl = {https://www.bibsonomy.org/bibtex/21ee096589a6d56867a23e8421f924bde/tmalsburg},
description = {Object perception as Bayesian inference. [Annu Rev Psychol. 2004] - PubMed Result},
doi = {10.1146/annurev.psych.55.090902.142005},
interhash = {f79c87db49591da0e0732ea2d4e1a61c},
intrahash = {1ee096589a6d56867a23e8421f924bde},
journal = {Annu Rev Psychol},
keywords = {bayesianinference perception vision},
pages = {271-304},
pmid = {14744217},
timestamp = {2009-06-13T13:03:49.000+0200},
title = {Object perception as Bayesian inference},
url = {http://www.ncbi.nlm.nih.gov/pubmed/14744217},
volume = 55,
year = 2004
}