Automated Visual Inspection Using a Distributed Blackboard Architecture

The framework of an automated vision system for monitoring quality control is presented where detection of various forms of defects is achieved by combining distributed artificial intelligence and image processing. A distributed blackboard architecture manages the processing of image data via an area of shared memory where the current understanding of the problem evolves. Registration into a common co-ordinate system and segmentation of reference and sensed images is performed in a multi-resolution fashion by intelligent agents that work in parallel and communicate with each other by means of the blackboard. Pixel-level fusion is then performed on registered images in order to exploit complementary and redundant data, allowing identification of suspected defects.