TR available --- Visual segmentation without classification in a model of V1

[Zhaoping Li]

Dear Connectionists,

        The following Technical report published by the AI publications
        office at MIT  may be accessed via 

        ftp://publications.ai.mit.edu/ai-publications/1500-1999/AIM-1613.ps

         TITLE:
        Visual segmentation without classification 
        in a model of the primary visual cortex 
        
        AUTHOR: 
        Zhaoping Li 
        
        ABSTRACT:
        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. 


Sincerely,

Zhaoping Li (zhaoping at ai.mit.edu)