摘要
提出面向对象联合变换相关器计算机模拟形态学理论,提出两种基于位表示法形态学相关算法(MMC)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,给出了改进的二维相关峰和谱图,提高了MMC对高相似度灰度图像的识别能力。
Faced object morphological correlation based on JTC computer simulation is presented. Two kinds of modified morphological correlation algorithm that are based on bit-representation decomposition are presented. The grayscale image is decomposed into a set of binary slices in the bit-representation decomposition. In the first algorithm, 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 speetrum image is gived. Computer-simulation results indicate that the modified algorithm can improve the discrimination capabilities with respect to the high similarity gray-scale images.
出处
《激光与红外》
CAS
CSCD
北大核心
2008年第7期712-715,共4页
Laser & Infrared
基金
江苏省重点学科经费资助
博士点基金资助
关键词
联合变换相关器
数学形态学
光学模式识别
joint transform correlator
mathematical morphology
optical pattern recognition
作者简介
余杨（1966-），男，硕士生导师，博士后，副教授，研究领域为光学信息处理，机器人视觉。E-mail：yuyang@njnu．edu．cn
