A NEW APPROACH FOR AGGREGATING EDGE POINTS INTO LINE SEGMENTS

A technique is presented for aggregating edge points into polylines wh ich can effectively represent object contours. The technique is based on a new formulation of Hough transform (HT) for detection of line seg ments. The space requirement of the HT is brought down by considering a different parameterization of straight lines. In this method, the pr ocess of edge linking and boundary approximation are combined into a s ingle algorithm. Consequently, the scheme is computationally more effi cient than the classical boundary approximation techniques which requi re a separate edge linking algorithm for preparing their input-the lin ked list of edge points. Experimental results presented here highlight the effectiveness of this method for approximating object boundaries of polygonal as well as curved shapes present in the images of complex multi-object scenes even in the presence of noise. Further, the paral lel algorithm proposed herein for implementation of this technique mak es it an ideal choice for real time applications.