数字图像处理在光学相关识别中的应用  

Application of Digital Image Processing in Optical Correlation Recognition

作　　者：王勇[1,2] 朱明[1] 

机构地区：[1]中国科学院长春光学精密机械与物理研究所,长春130033 [2]中国科学院研究生院,北京100039

出　　处：《光电子技术》2009年第4期251-256,共6页Optoelectronic Technology

基　　金：国家"863"计划资助项目(2005AA778032)

摘　　要：光学模式识别信息处理容量大,运算速度快,但精度不高,存储不灵活,不易判断控制和分析。联合变换相关器在光学图像相关识别中得到了广泛的应用。为提高联合变换相关器的性能,将数字图像处理技术引入光学相关识别中,主要体现在对联合图像进行预处理以及对联合功率谱的滤波处理。详细阐述了国内外常用的联合图像预处理算法和功率谱滤波算法,并对这些算法在光学相关识别中的应用效果进行了比较研究。The virtues of optical pattern recognition lies in its high capacity and speed for signal processing, but its judgement, controlling and analysis are difficult because of its poor precision and agility. Joint transform correlator are widely used in optical image correlation recognition. To improve the performance of joint transform correlator, digital image processing technology are used in optical correlation recognition such as the preprocessing for joint image and filtering for power spectrum. Several joint image preprocessing methods and power spectrum filtering algorithms are introduced, their applying effect in joint transform correlator are compared.

关 键 词：数字图像处理 模式识别 联合变换相关器 预处理 

分 类 号：O472.8[理学—半导体物理]