We present an optical technique for finding the centroids of nonoverlapping objects in a scene, thus locating the objects and preserving the underlying advantage of matched filtering approaches to pattern recognition. One is then free to extract any feature desired at these centroid locations rather than restricted to the matched filter test statistic. Furthermore, this allows general feature extraction avoiding prior scene segmentation into individual objects. The technique can also be used for tracking the motion of rigid or nonrigid objects. It consists of cross-correlating the input f(x,y) with a windowed version of the function x + iy and detecting the zeros of the magnitude of the resulting correlation. At these points the x and y first moments vanish. The window is selected based on the size and separation of the objects in a scene. Experimental verification as well as restrictions are also presented.
© 1987 Optical Society of AmericaFull Article | PDF Article