PYRAMID ADAPTIVE DYNAMIC HOUGH TRANSFORM TO DETECT EDGES WITH ARBITRARY SHAPES

A computationally efficient pyramid adaptive dynamic Hough transform ( PADHT) is proposed to detect edges with arbitrary shapes and without p rior knowledge. The binary pyramid structure is generated first. The e dge map at the top pyramid level is obtained by using PADHT next, The edge map at each lower pyramid level is generated by PADHT also, but i n a much smaller area determined by the edge map at the level immediat ely above. The analytic expressions of the arbitrary edge curves for t he dynamic Hough transform are approximated by the rational Gaussian f unctions. The parameters of the Gaussian functions and the accumulated areas are changed adaptively according to the set of accumulated poin ts. An energy function is used to determine which set of accumulated p oints represents the edge curve. (C) 1997 Society of Photo-Optical Ins trumentation Engineers.