Neural associative processing of document images

Binary neural associative memories are attractive for image processing because of their speed of operation for learning associations and for recalling them. We have added feedback to a feedforward associative memory, to produce a pattern completion network which performs translation-invariant pattern completion, and at the same time resolves contradictory image information. The image completion is realised as a complete labelling of the features comprising known compound objects in the image. The network has been used for high speed document image analysis