A Model of Contour Integration in Early Visual Cortex. Mundhenk, T. N. & Itti, L. In Lecture Notes in Computer Science, volume 2525, pages 80-89, Nov, 2002. abstract bibtex We have created an algorithm to integrate contour elements and find the salience value of them. The algorithm consists of basic long-range orientation specific neural connections as well as a group suppression gain control and a fast plasticity term to explain interaction beyond a neurons normal size range. Integration is executed as a series of convolutions on 12 orientation filtered images augmented by the nonlinear fast plasticity and group suppression terms. Testing done on a large number of artificially generated Gabor element contour images shows that the algorithm is effective at finding contour elements within parameters similar to that of human subjects. Testing of real world images yields reasonable results and shows that the algorithm has strong potential for use as an addition to our already existent vision saliency algorithm.
@inproceedings{ Mundhenk_Itti02bmcv,
author = {T. N. Mundhenk and L. Itti},
title = {A Model of Contour Integration in Early Visual Cortex},
abstract = { We have created an algorithm to integrate contour elements
and find the salience value of them. The algorithm consists of basic
long-range orientation specific neural connections as well as a group
suppression gain control and a fast plasticity term to explain
interaction beyond a neurons normal size range. Integration is
executed as a series of convolutions on 12 orientation filtered images
augmented by the nonlinear fast plasticity and group suppression
terms. Testing done on a large number of artificially generated Gabor
element contour images shows that the algorithm is effective at
finding contour elements within parameters similar to that of human
subjects. Testing of real world images yields reasonable results and
shows that the algorithm has strong potential for use as an addition
to our already existent vision saliency algorithm.},
booktitle = {Lecture Notes in Computer Science},
volume = {2525},
year = {2002},
month = {Nov},
pages = {80-89},
type = {mod;bu;cv},
file = { http://iLab.usc.edu/publications/doc/Mundhenk_Itti02bmcv.pdf },
review = {full/conf}
}
Downloads: 0
{"_id":{"_str":"5298a19f9eb585cc260007fd"},"__v":0,"authorIDs":[],"author_short":["Mundhenk, T.<nbsp>N.","Itti, L."],"bibbaseid":"mundhenk-itti-amodelofcontourintegrationinearlyvisualcortex-2002","bibdata":{"html":"<div class=\"bibbase_paper\"> \n\n\n<span class=\"bibbase_paper_titleauthoryear\">\n\t<span class=\"bibbase_paper_title\"><a name=\"Mundhenk_Itti02bmcv\"> </a>A Model of Contour Integration in Early Visual Cortex.</span>\n\t<span class=\"bibbase_paper_author\">\nMundhenk, T. N.; and Itti, L.</span>\n\t<!-- <span class=\"bibbase_paper_year\">2002</span>. -->\n</span>\n\n\n\nIn\n<i>Lecture Notes in Computer Science</i>, volume 2525, page 80-89, Nov 2002.\n\n\n\n\n\n<br class=\"bibbase_paper_content\"/>\n\n<span class=\"bibbase_paper_content\">\n \n \n \n <a href=\"javascript:showBib('Mundhenk_Itti02bmcv')\"\n class=\"bibbase link\">\n <!-- <img src=\"http://www.bibbase.org/img/filetypes/bib.png\" -->\n\t<!-- alt=\"A Model of Contour Integration in Early Visual Cortex [bib]\" -->\n\t<!-- class=\"bibbase_icon\" -->\n\t<!-- style=\"width: 24px; height: 24px; border: 0px; vertical-align: text-top\"><span class=\"bibbase_icon_text\">Bibtex</span> -->\n BibTeX\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n <a class=\"bibbase_abstract_link bibbase link\"\n href=\"javascript:showAbstract('Mundhenk_Itti02bmcv')\">\n Abstract\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n\n \n \n \n</span>\n\n<div class=\"well well-small bibbase\" id=\"bib_Mundhenk_Itti02bmcv\"\n style=\"display:none\">\n <pre>@inproceedings{ Mundhenk_Itti02bmcv,\n author = {T. N. Mundhenk and L. Itti},\n title = {A Model of Contour Integration in Early Visual Cortex},\n abstract = { We have created an algorithm to integrate contour elements\nand find the salience value of them. The algorithm consists of basic\nlong-range orientation specific neural connections as well as a group\nsuppression gain control and a fast plasticity term to explain\ninteraction beyond a neurons normal size range. Integration is\nexecuted as a series of convolutions on 12 orientation filtered images\naugmented by the nonlinear fast plasticity and group suppression\nterms. Testing done on a large number of artificially generated Gabor\nelement contour images shows that the algorithm is effective at\nfinding contour elements within parameters similar to that of human\nsubjects. Testing of real world images yields reasonable results and\nshows that the algorithm has strong potential for use as an addition\nto our already existent vision saliency algorithm.},\n booktitle = {Lecture Notes in Computer Science},\n volume = {2525},\n year = {2002},\n month = {Nov},\n pages = {80-89},\n type = {mod;bu;cv},\n file = { http://iLab.usc.edu/publications/doc/Mundhenk_Itti02bmcv.pdf },\n review = {full/conf}\n}</pre>\n</div>\n\n\n<div class=\"well well-small bibbase\" id=\"abstract_Mundhenk_Itti02bmcv\"\n style=\"display:none\">\n We have created an algorithm to integrate contour elements and find the salience value of them. The algorithm consists of basic long-range orientation specific neural connections as well as a group suppression gain control and a fast plasticity term to explain interaction beyond a neurons normal size range. Integration is executed as a series of convolutions on 12 orientation filtered images augmented by the nonlinear fast plasticity and group suppression terms. Testing done on a large number of artificially generated Gabor element contour images shows that the algorithm is effective at finding contour elements within parameters similar to that of human subjects. Testing of real world images yields reasonable results and shows that the algorithm has strong potential for use as an addition to our already existent vision saliency algorithm.\n</div>\n\n\n</div>\n","downloads":0,"bibbaseid":"mundhenk-itti-amodelofcontourintegrationinearlyvisualcortex-2002","role":"author","year":"2002","volume":"2525","type":"mod;bu;cv","title":"A Model of Contour Integration in Early Visual Cortex","review":"full/conf","pages":"80-89","month":"Nov","key":"Mundhenk_Itti02bmcv","id":"Mundhenk_Itti02bmcv","file":"http://iLab.usc.edu/publications/doc/Mundhenk_Itti02bmcv.pdf","booktitle":"Lecture Notes in Computer Science","bibtype":"inproceedings","bibtex":"@inproceedings{ Mundhenk_Itti02bmcv,\n author = {T. N. Mundhenk and L. Itti},\n title = {A Model of Contour Integration in Early Visual Cortex},\n abstract = { We have created an algorithm to integrate contour elements\nand find the salience value of them. The algorithm consists of basic\nlong-range orientation specific neural connections as well as a group\nsuppression gain control and a fast plasticity term to explain\ninteraction beyond a neurons normal size range. Integration is\nexecuted as a series of convolutions on 12 orientation filtered images\naugmented by the nonlinear fast plasticity and group suppression\nterms. Testing done on a large number of artificially generated Gabor\nelement contour images shows that the algorithm is effective at\nfinding contour elements within parameters similar to that of human\nsubjects. Testing of real world images yields reasonable results and\nshows that the algorithm has strong potential for use as an addition\nto our already existent vision saliency algorithm.},\n booktitle = {Lecture Notes in Computer Science},\n volume = {2525},\n year = {2002},\n month = {Nov},\n pages = {80-89},\n type = {mod;bu;cv},\n file = { http://iLab.usc.edu/publications/doc/Mundhenk_Itti02bmcv.pdf },\n review = {full/conf}\n}","author_short":["Mundhenk, T.<nbsp>N.","Itti, L."],"author":["Mundhenk, T. N.","Itti, L."],"abstract":"We have created an algorithm to integrate contour elements and find the salience value of them. The algorithm consists of basic long-range orientation specific neural connections as well as a group suppression gain control and a fast plasticity term to explain interaction beyond a neurons normal size range. Integration is executed as a series of convolutions on 12 orientation filtered images augmented by the nonlinear fast plasticity and group suppression terms. Testing done on a large number of artificially generated Gabor element contour images shows that the algorithm is effective at finding contour elements within parameters similar to that of human subjects. Testing of real world images yields reasonable results and shows that the algorithm has strong potential for use as an addition to our already existent vision saliency algorithm."},"bibtype":"inproceedings","biburl":"http://ilab.usc.edu/publications/src/ilab.bib","downloads":0,"search_terms":["model","contour","integration","early","visual","cortex","mundhenk","itti"],"title":"A Model of Contour Integration in Early Visual Cortex","year":2002,"dataSources":["wedBDxEpNXNCLZ2sZ"]}