一种提高光学相关模式识别准确性的后处理方法  

A Postprocessing Method for Improving the Accuracy of the Optical Correlation Pattern Recognition

作　　者：刘海松[1] 邬敏贤[1] 金国藩[1] 成罡[1] 何庆声[1] 

机构地区：[1]清华大学精密测试技术与仪器国家重点实验室

出　　处：《光学学报》1999年第7期924-928,共5页Acta Optica Sinica

基　　金：国家科委863高技术资助项目;国家自然科学基金

摘　　要：将基于绝对差算法的最小距离度量方法用于光学相关器产生的相关结果灰度图像的相似性度量，并以此为依据给出待识别图像与参考图像之间的相似性结论；避免了传统的以相关峰取阈为判决依据引起的误判现象，提高了判决准确率，甚至可以对由灰度图像直接做光学相关得到的低质量相关结果给出准确判断，从而避免了对灰度图像做二值化及编码处理等烦琐的预处理工作。采用非相干光相关器为光学实现硬件并给出了实验结果。Minimal distance measure method based on an absolute difference measure is applied to the similarity measure among the optical correlation resultant images, and then the similarity conclusion between the image to be tested and the reference image can be deduced. By this method, the false recognition which often occurs when the traditional correlation peak thresholding method is used, can be avoided and the recognition accuracy can be greatly improved. Even the low quality correlation output between two gray scale images can be processed so that the complex preprocessing of the gray scale images, such as the binarization and encoding, can be omitted. The optical experimental results implemented on an incoherent optical correlator are given.

关 键 词：模式识别 光学相关 后处理 相似性度量 绝对差 

分 类 号：O438[机械工程—光学工程]