Neural Network Capable of Amodal Completion

Abstract

When some parts of a pattern are occluded by other objects, the visual system can often estimate the shape of missing portions from visible parts of the contours. This paper proposes a neural network model capable of such function, which is called amodal completion. The model is a hierarchical multi-layered network that has bottom-up and top-down signal paths. It contains cells of area V1, which respond selectively to edges of a particular orientation, and cells of area V2, which respond selectively to a particular angle of bend. Using the responses of bend-extracting cells, the model predicts the curvature and location of the occluded contours. Missing portions of the contours are gradually extrapolated and interpolated from the visible contours. Computer simulation demonstrates that the model performs amodal completion to various stimuli in a similar way as observed by psychological experiments.