Coding facial images for database retrieval using a self organising neural network

Addresses some of the problems of accessing database images which do not contain any indexing information. More specifically, the authors investigate methods of automating search strategies for facial images which currently rely on human operators to match the target against a number of images in the database. Such problems might include the extraction of facial photographs from a library given a suspect. The object of the retrieval mechanism is to narrow down the search space for final perusal by the human operator. This work shows how an automatic feature extraction system based on a Self Organising Neural Network topology can provide the foundations for a facial image database retrieval system