GRAPH-BASED FEATURE MATCHING USING DESCRIPTIVE AND RELATIONAL PARAMETERS

A graph-based matching algorithm for edge features was developed. It conducts a breadth-first search in two next-neighbor graphs starting at hypothetically matched feature pairs. A match is established by comparing feature properties using a match function. Main advantage of the matching algorithm is its applicability to various domains, such as stereo vision or matching images and GIS data. Digitized stereo image pairs for the investigation of automobile accidents are used to illustrate the method. For objects with distinctive edges, 80 to 90 percent of the resultant feature pairs were found to be correct.