基于群体智能边缘提取算法的联合变换相关器  

Joint transform correlator based on joint image feature extraction using swarm intelligence method

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,吉林长春130033 [2]中国科学院研究生院,北京100039

出　　处：《激光与红外》2009年第10期1126-1130,共5页Laser & Infrared

基　　金：国家"863"计划(No.2005AA778032)资助

摘　　要：为提取联合变换相关器输入面图像的边缘,改善相关器的识别效果,提出了一种基于群体智能的图像特征提取方法,并将其应用于联合变换相关器的输入面图像预处理中。实验结果表明该算法有效提取了图像的边缘,锐化了相关峰,提高了联合变换相关器的目标识别能力。群体智能计算机并行算法与联合变换相关器光学并行系统相结合,为实现实时高效的光电混合目标识别系统奠定了坚实的理论基础。An image feature extraction method based on swarm intelligence is used in the preprocessing of joint image in joint transform correlator. The swarm intelligence is superior to the conventional image processing method in its robust, flexible, fault tolerant, scalable, and highly parallelizable characteristic. The output results from the classical JTC without image preprocessing and the JTC with Sobel operator based joint image feature extraction are compared with that of the JTC using the swarm intelligence to extract the feature of joint image. Experiment results show the performanee improvement of JTC using the feature extraction method based on swarm intelligence.

关 键 词：群体智能 联合变换相关器 实时性 目标识别 

分 类 号：TP751.2[自动化与计算机技术—检测技术与自动化装置]