The design and application of associative memories for scene analysis
James Austin · 1986
This thesis investigates a novel scene analysis system that determines the identity and the relative positions of unconstr~ined objects within a natural three dimensional gr~y scale image. Images may be of 'block filled ' or 'line drawn ' occluded shapes. It utilises the occluding information to discover the relative depth of objects in the scene. The system incorporates associative memories, the N tuple pattern recognition process, movable multiple resolution windows and edge detection. The structure and performance of the system and its subsystems is reported. The associative memory incorporates a novel. recall procedure which has uses outside the application given here. The work incorporates ideas from the neurophysiology of the human visu~l system to overcome some of the problems encountered. Acknowledgments I would like to thank Prof. Igor Aleksander for the initial project