Grouping for Recognition

This paper presents a new method of grouping edges in order to recognize objects. This grouping method succeeds on images of both two-and three-dimensional objects. We order groups of edges based on the likelihood that a single object produced them. This allows the recognition system to consider rst the collections of edges most likely to lead to the correct recognition of objects. The grouping module estimates this likelihood using the distance that separates edges and their relative orientation. This ordering greatly reduces the amount of computation required to locate objects. Surprisingly, in some circumstances grouping can also improve the accuracy of a recognition system. We test the grouping system in two ways. First, we use it in a recognition system that handles libraries of two-dimensional, polygonal objects. Second, we show comparable performance of the grouping system on images of two-and three-dimensional objects. This demonstrates that the grouping system could produce signiicant improvements in the performance of a three-dimensional recognition system.