Invariant recognition of cluttered scenes by a self-organizing ART architecture: figure-ground separation
Stephen Grossberg, Lonce L. Wyse · 2002
A neural network model, called an FBF (feature-boundary-feature) network, is proposed for automatic parallel separation of multiple image figures from each other and their backgrounds in noisy gray-scale or multicolored images. The system is capable of automatic figure-ground separation, which is accomplished by iterating operations of a feature contour system (FCS) and a boundary contour system (BCS) that have been derived from an analysis of biological vision. The FCS operations include shunting nets to compensate for variable illumination and diffusion nets to control filling-in. The BCS operations include oriented filters joined to competitive and cooperative interactions designed to detect, regularize, and complete boundaries in up to 50% noise, while suppressing the noise.>