AUTHOR=Tschechne Stephan , Neumann Heiko
TITLE=Hierarchical representation of shapes in visual cortex—from localized features to figural shape segregation
JOURNAL=Frontiers in Computational Neuroscience
VOLUME=Volume 8 - 2014
YEAR=2014
URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2014.00093
DOI=10.3389/fncom.2014.00093
ISSN=1662-5188
ABSTRACT=Visual structures in the environment are effortlessly segmented into image regions and those combined to a representation of surfaces and prototypical objects. Such a perceptual organization is performed by complex neural mechanisms in the visual cortex of primates. Multiple mutually connected areas in the ventral cortical pathway receive visual input and extract local form features that are subsequently grouped into increasingly complex, more meaningful image elements. At this stage, highly articulated changes in shape boundary as well as very subtle curvature changes contribute to the perception of an object.
We propose a recurrent computational network architecture that utilizes a hierarchical distributed representation of shape features to encode boundary features over different scales of resolution. Our model makes use of neural mechanisms that model the processing capabilities of early and intermediate stages in visual cortex, namely areas V1-V4 and IT. We suggest that multiple specialized component representations interact by feedforward hierarchical processing that is combined with feedback from representations generated at higher stages. In so doing, global configurational as well as local information is available to distinguish changes in the object's contour. Once the outline of a shape has been established, contextual contour configurations are used to assign border ownership directions and thus achieve segregation of figure and ground. This combines separate findings about the generation of cortical shape representation using hierarchical representations with figure-ground segregation mechanisms.
Our model is probed with a selection of artificial and real world images to illustrate processing results at different processing stages. We especially highlight how modulatory feedback connections contribute to the processing of visual input at various stages in the processing hierarchy.