Visual Segmentation without Classification in a Model of the Primary Visual Cortex
Stimuli outside classical receptive fields significantly influence the neurons' activities in primary visual cortex. We propose that such contextual influences are used to segment regions by detecting the breakdown of homogeneity or translation invariance in the input, thus computing glob...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/7247 |
| _version_ | 1826191979833196544 |
|---|---|
| author | Li, Zhaoping |
| author_facet | Li, Zhaoping |
| author_sort | Li, Zhaoping |
| collection | MIT |
| description | Stimuli outside classical receptive fields significantly influence the neurons' activities in primary visual cortex. We propose that such contextual influences are used to segment regions by detecting the breakdown of homogeneity or translation invariance in the input, thus computing global region boundaries using local interactions. This is implemented in a biologically based model of V1, and demonstrated in examples of texture segmentation and figure-ground segregation. By contrast with traditional approaches, segmentation occurs without classification or comparison of features within or between regions and is performed by exactly the same neural circuit responsible for the dual problem of the grouping and enhancement of contours. |
| first_indexed | 2024-09-23T09:04:18Z |
| id | mit-1721.1/7247 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:04:18Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/72472019-04-10T20:32:31Z Visual Segmentation without Classification in a Model of the Primary Visual Cortex Li, Zhaoping Stimuli outside classical receptive fields significantly influence the neurons' activities in primary visual cortex. We propose that such contextual influences are used to segment regions by detecting the breakdown of homogeneity or translation invariance in the input, thus computing global region boundaries using local interactions. This is implemented in a biologically based model of V1, and demonstrated in examples of texture segmentation and figure-ground segregation. By contrast with traditional approaches, segmentation occurs without classification or comparison of features within or between regions and is performed by exactly the same neural circuit responsible for the dual problem of the grouping and enhancement of contours. 2004-10-20T21:04:02Z 2004-10-20T21:04:02Z 1997-08-01 AIM-1613 CBCL-153 http://hdl.handle.net/1721.1/7247 en_US AIM-1613 CBCL-153 309472 bytes 368749 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Li, Zhaoping Visual Segmentation without Classification in a Model of the Primary Visual Cortex |
| title | Visual Segmentation without Classification in a Model of the Primary Visual Cortex |
| title_full | Visual Segmentation without Classification in a Model of the Primary Visual Cortex |
| title_fullStr | Visual Segmentation without Classification in a Model of the Primary Visual Cortex |
| title_full_unstemmed | Visual Segmentation without Classification in a Model of the Primary Visual Cortex |
| title_short | Visual Segmentation without Classification in a Model of the Primary Visual Cortex |
| title_sort | visual segmentation without classification in a model of the primary visual cortex |
| url | http://hdl.handle.net/1721.1/7247 |
| work_keys_str_mv | AT lizhaoping visualsegmentationwithoutclassificationinamodeloftheprimaryvisualcortex |