Visual segmentation without classification in a model of the primary visual cortex.
Center for Biological & Computational Learning (CBCL), Massachusetts Institute of Technology: Cambridge, US.
Stimuli outside classical receptive fields significantly influence the neurons' activities in primary visual cortex [1, 2, 3, 4, 5]. 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.
|Title:||Visual segmentation without classification in a model of the primary visual cortex|
|Open access status:||An open access version is available from UCL Discovery|
|Additional information:||© Massachusetts Institute of Technology, 1997. This paper is made available for educational purposes only and not for profit or commercial use|
|UCL classification:||UCL > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neuroscience Unit|
Archive Staff Only