Applications of SOAR to monochromatic image restoration

This study proposes a novel autoassociator for associative storage of gray scale images. An autoassociator is a system capable of completing an incomplete pattern, when it is presented as part of a learned pattern. Patterns in the proposed associative architecture are gray scale images with integer values. The proposed system, based on a previously developed technique called “SOAR”, is superior to existing techniques using binary neural networks for associative storage of gray scale images in both the computational complexity and the processing unit requirements. The proposed system is parallel in nature and can be implemented using a synchronous or asynchronous parallel system with no added complexity