Fast normalized neural processors for pattern detection based on cross correlation implemented in the frequency domain

Neural networks have shown good results for detecting a certain pattern in a given image. In this paper, fast neural networks for pattern detection are presented. Such neural processors are designed based on cross correlation in the frequency domain between the input image and the weights of neural networks. New general formulas for fast cross correlation as well as the speed up ratio are given. Also, commutative cross correlation is achieved. Furthermore, an approach to reduce the computation steps required by these fast neural networks for the searching process is presented. The principle of divide and conquer strategy is applied through image decomposition. Each image is divided into small in size sub-images and then each one is tested separately by using a single fast neural processor. Compared with conventional and fast neural networks, experimental results show that a speed up ratio is achieved when applying this technique to locate different patterns automatically in cluttered scenes. Furthermore, faster pattern detection is obtained by using parallel processing techniques to test the resulting sub-images at the same time using the same number of fast neural networks. In contrast to fast neural networks, the speed up ratio is increased with the size of the input image when using fast neural networks and image decomposition. Our previous work solved the problem of local sub-image normalization in the frequency domain. Here, the effect of image normalization on the speed up ratio of pattern detection is presented. Simulation results show that local sub-image normalization through weight normalization is faster than sub-image normalization in the spatial domain. Moreover, the overall speed up ratio of the detection process is increased as the normalization of weights is done off line. Copyright © 2006, Australian Computer Society Inc.