Recognizing and segmenting objects in clutter. Bravo, M. & Farid, H. Vision Res., 44:385--396, Feb, 2004. abstract bibtex When viewing a cluttered scene, observers may not be able to segment whole objects prior to recognition. Instead, they may segment and recognize these objects in a piecemeal way. Here we test whether observers can use the appearance of one object part to predict the location and appearance of other object parts. During several training sessions, observers studied an object against a blank background. They then viewed this object against a background of clutter that camouflaged some parts of the object while leaving other parts salient. The observer's task was to find the camouflaged part. We varied the symmetry of the salient part with the expectation that as this symmetry decreased, the information about the camouflaged part's location and appearance would increase and this would facilitate search. Our results suggest that observers can use the salient part to predict the location, but not the appearance, of the camouflaged part.
@article{ Bravo_Farid04,
author = {Bravo, M.J. and Farid, H.},
title = {{{R}ecognizing and segmenting objects in clutter}},
journal = {Vision Res.},
year = {2004},
volume = {44},
pages = {385--396},
month = {Feb},
abstract = {When viewing a cluttered scene, observers may not be able to segment
whole objects prior to recognition. Instead, they may segment and
recognize these objects in a piecemeal way. Here we test whether
observers can use the appearance of one object part to predict the
location and appearance of other object parts. During several training
sessions, observers studied an object against a blank background.
They then viewed this object against a background of clutter that
camouflaged some parts of the object while leaving other parts salient.
The observer's task was to find the camouflaged part. We varied the
symmetry of the salient part with the expectation that as this symmetry
decreased, the information about the camouflaged part's location
and appearance would increase and this would facilitate search. Our
results suggest that observers can use the salient part to predict
the location, but not the appearance, of the camouflaged part.}
}
Downloads: 0
{"_id":"CZEMSD73X3SRg8aiN","bibbaseid":"bravo-farid-recognizingandsegmentingobjectsinclutter-2004","downloads":0,"creationDate":"2015-02-08T05:14:39.677Z","title":"Recognizing and segmenting objects in clutter","author_short":["Bravo, M.","Farid, H."],"year":2004,"bibtype":"article","biburl":"http://cnslab.mb.jhu.edu/niebase.bib","bibdata":{"abstract":"When viewing a cluttered scene, observers may not be able to segment whole objects prior to recognition. Instead, they may segment and recognize these objects in a piecemeal way. Here we test whether observers can use the appearance of one object part to predict the location and appearance of other object parts. During several training sessions, observers studied an object against a blank background. They then viewed this object against a background of clutter that camouflaged some parts of the object while leaving other parts salient. The observer's task was to find the camouflaged part. We varied the symmetry of the salient part with the expectation that as this symmetry decreased, the information about the camouflaged part's location and appearance would increase and this would facilitate search. Our results suggest that observers can use the salient part to predict the location, but not the appearance, of the camouflaged part.","author":["Bravo, M.J.","Farid, H."],"author_short":["Bravo, M.","Farid, H."],"bibtex":"@article{ Bravo_Farid04,\n author = {Bravo, M.J. and Farid, H.},\n title = {{{R}ecognizing and segmenting objects in clutter}},\n journal = {Vision Res.},\n year = {2004},\n volume = {44},\n pages = {385--396},\n month = {Feb},\n abstract = {When viewing a cluttered scene, observers may not be able to segment\n\twhole objects prior to recognition. Instead, they may segment and\n\trecognize these objects in a piecemeal way. Here we test whether\n\tobservers can use the appearance of one object part to predict the\n\tlocation and appearance of other object parts. During several training\n\tsessions, observers studied an object against a blank background.\n\tThey then viewed this object against a background of clutter that\n\tcamouflaged some parts of the object while leaving other parts salient.\n\tThe observer's task was to find the camouflaged part. We varied the\n\tsymmetry of the salient part with the expectation that as this symmetry\n\tdecreased, the information about the camouflaged part's location\n\tand appearance would increase and this would facilitate search. Our\n\tresults suggest that observers can use the salient part to predict\n\tthe location, but not the appearance, of the camouflaged part.}\n}","bibtype":"article","id":"Bravo_Farid04","journal":"Vision Res.","key":"Bravo_Farid04","month":"Feb","pages":"385--396","title":"Recognizing and segmenting objects in clutter","type":"article","volume":"44","year":"2004","bibbaseid":"bravo-farid-recognizingandsegmentingobjectsinclutter-2004","role":"author","urls":{},"downloads":0},"search_terms":["recognizing","segmenting","objects","clutter","bravo","farid"],"keywords":[],"authorIDs":[],"dataSources":["ErLXoH8mqSjESnrN5"]}