Use of top-down signals for restoring partly occluded patterns
Kunihiko Fukushima · 2003
Proposes a neural network model that has the ability to repair the missing portions of partly occluded patterns. It is a multi-layered hierarchical neural network, in which visual information is processed by interaction of bottom-up and top-down signals. If a partly occluded pattern is unfamiliar to the model, the model tries to reconstruct the original shape by extrapolating the contours of the unoccluded part of the pattern. If the pattern has already been learned by the model, the model recognizes it and tries to complete the shape using the learned information on the shape of the pattern. The model does not use a simple template matching method. It can accept even deformed versions of learned patterns.