Shape matching using a modified Generalized Hough Transform

Most of the work related to shape matching in digital photogrammetry utilizes parametrized shapes, where shapes are approximated by analytical functions or polygons. In this work a general matching algorithm is presented based on the principles of Generalized Hough Transform (GHT). It utilizes non-parametrized shapes and does not require a polygonal approximation nor does it depend on curve critical points or breakpoints, which may fail to exist due to noise and occlusions. An approach is also presented for modifying the GHT in order to overcome the shortcoming of its not being rotation invariant. In the matching algorithm, edge segments are extracted from the overlapping images using Canny's edge detector and an edge tracking algorithm. The matching technique is applied for each edge segment in one image and its matching candidates in the other image. A consistency check for the matching results is performed utilizing relationships among edge segments in both images. Tests showed the efficiency of the matching approach in dealing with broken and occluded edge segments and in achieving good and robust results.