Figure-Ground Organization in Natural Scenes: Performance of a Recurrent Neural Model Compared with Neurons of Area V2.

ABSTRACT: A crucial step in understanding visual input is its organization into meaningful components, in particular object contours and partially occluded background structures. This requires that all contours are assigned to either the foreground or the background (border ownership assignment). While earlier studies showed that neurons in primate extrastriate cortex signal border ownership for simple geometric shapes, recent studies show consistent border ownership coding also for complex natural scenes. In order to understand how the brain performs this task, we developed a biologically plausible recurrent neural network that is fully image computable. Our model uses local edge detector ( B ) cells and grouping ( G ) cells whose activity represents proto-objects based on the integration of local

SUBMITTER: Hu B 

PROVIDER: S-EPMC6635809 | biostudies-literature | 2019 May/Jun

REPOSITORIES: biostudies-literature