Optimal algorithms for target location in nonhomogeneous binary images

Binary images appear in various pattern recognition applications. It is thu s important to design pattern recognition algorithms that are optimal for s uch images. We address the problem of target location in binary images pert urbed with nonhomogeneous background noise. The proposed algorithm optimize s the likelihood ratio between the hypotheses that the target is present wi thin a small subwindow of the image and that it is not present in this subw indow. The algorithm is shown to consist of two correlation operations and a few pointwise nonlinear transformations. With numerical simulations, we i llustrate the efficiency of this technique, especially in the presence of s trongly nonhomogeneous background noise. (C) 1998 Optical Society of Americ a [S0740-3232(98)00812-6].