EDGE FINDING, SEGMENTATION OF EDGES AND RECOGNITION OF COMPLEX OBJECTS

This paper describes an approach to the recognition of real-world objects such as books or a telephone on a desk. The system consists of (l) edge finding process which extracts edges of curved objects from light intensity data, (2) segmentation of the edges into straight lines or elliptic curves, (3) recognition of objects by matching the liner, to the models, and (4) simple supervisor. The module (1), (2) and ( 3) interact with each other through a simple supervisor so that the system can locate given objects quickly-First, most reliable edges are found and segmented, and then recognition i r. attempted using segmented lines. If recognition is not successful, less reliable edges are searched for, arid recognition is retried. An example of locating a lamp, a book stand and a telephone is shown. 1