A PARALLEL, DISTRIBUTED AND ASSOCIATIVE APPROACH FOR SEARCHING IMAGE PATTERNS WITH HOLOGRAPHIC DYNAMICS

This paper presents a new associative pattern-matching network based o n a digital adaptation of optical holography. Unlike any existing neur al network or associative memories, it can localize its search dynamic ally on any subset of the pattern space and at the same time generate a feedback on the quality of the match. Current associative memories b ased on neuro computing are unable to support such meta-interactions. The scheme involves adaptive 'enfolding' of the raw massive search spa ce into a holograph and direct regeneration of the matched target patt ern during a search. The search process is a constant-time operation c ompared to traditional algorithm approaches, inherently parallelizable , and is an excellent candidate for hardware or optical implementation . This new technique is expected to facilitate significantly applicati ons that require direct pattern matching in massive image repositories in real time. Target recognition, visual query content-based image re trieve and automatic index-extraction are just a few of such applicati ons. (C) 1997 Academic Press Limited.