Restoring Partly Occluded Patterns: A Neural Network Model with Backward Paths

Abstract

This paper proposes a neural network model that has an ability to restore 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. Occluded parts of a pattern are reconstructed mainly by feedback signals from the highest stage of the network, while the unoccluded parts are reproduced mainly by signals from lower stages. The model does not use a simple template matching method. It can restore even deformed versions of learned patterns.