面向对象形态学算法模拟识别非对称灰度数字图像研究

Faced Object Morphological Algorithm Recognize Dissymmetry Digital Gray Image Simulately

用数字图像处理纯软件位图的方法实现形态学算法,借助联合变换相关器理论,提出面向对象计算机模拟形态学理论识别非对称灰度图像,提出两种基于位表示法形态学相关算法(MM C)的改进算法,通过提取基于位表示法的图像片边缘特征或二元化基于位表示法的图像片功率谱,给出了改进的识别非对称灰度图像的二维相关峰和谱图,鉴别率明显提高,提高了MM C的识别能力。该模拟可以用数字图象处理纯软件的方法实现具有实用性。

Morphological correlation is realized by digital image processing method. In virtue of JTC theory, faced object computer simulation morphological theory for recognizing dissymmetry gray-scale image is presented. Two kinds of modified morphological correlation algorithm （MMC） that are based on bit-representation decomposition are presented. The gray-scale image is decomposed into a set of binary slices in the bit-representation decomposition. In the first algo- rithm,the edge of each pair of slices is detected. In the second algorithm, the joint power spectrum of each pair is binarized or the summation of the joint power spectrum of these pairs is binarized. Modified two dimention correlation peak and spectrum image is gived for recogmizing the dissymmetry image. The MMC discrimination capabilities with respect to the high similarity gray-scale images is advanced. The simulation can be realized and have practicability with digital image processing software method.