灰度人脸识别形态学相关的一般理论研究

提出一般形态学相关概念，并提出一种小型联合变换相关器的硬件设计以实现一般形态学相关.提出两种改进的一般形态学相关算法，灰度图像按某种分解方法分解成一系列二值图像片.在第一种算法中，每片二值联合图像片的边缘被检测，其功率谱求和.在第二种算法中，一种情况是每片的联合变换功率谱被二值化或细化再求和；另一种情况是这些片的联合变换功率谱的总和被二值化或细化.计算机模拟结果表明，改进后的算法能改善高相似度灰度人脸图像识别的鉴别率.

General Theory Research on Morphological Correlation for Gray-Scale Face Recognition

General morphological correlation(GMC) is proposed and hardware design for a compact joint transform correlator(JTC) is proposed in order to implement GMC. Two kinds of modified general morphological correlation is studied. The gray-scale image is decomposed into a set of binary image slices in certain decomposition method. In the first algorithm, the edge of each binary joint image slice is detected and the joint power spectrum of which is summed. In the second algorithm, one situation is that the joint power spectrum of each pair is binarized or thinned and then summed,and another situation is that the summation of the joint power spectrums of these pairs is binarized or thinned. Computer-simulation results indicate that the modified algorithm can improve the discrimination capabilities with respect to the high similarity gray-scale face images.