基于几何匹配和分合算法的生物特征识别技术在公安视频监控中人脸识别的应用研究

Application study of police face recognition video monitor system based on biometric technology of geometrical matching and split-merge

目的研究基于几何匹配和分合算法的生物特征识别技术,及其在公安视频监控中人脸识别的应用。方法在图像分割部分,实现了经典的分合算法,并且使用成组算法改进了分合的效果。在人脸匹配部分,实现了基于眼睛和嘴的几何模型匹配,并对评价函数的构造进行了研究。结果通过对600个样本测试,正确检测率为88%,误检率为2%。结论实验证明,对于尺寸足够大的清晰的正面单个/多个人脸情形能够正确检测定位。

[ Objective ] This paper studied biometrie technology of geometrical matching and split-merge, and the applications in police face recognition video monitor system. [ Methods ] In the section of preprocessing, special methods to enhance the contrast between face features and face skin and a local thresholding method were employed so that the result of the preprocessing was improved. In the section of image segmentation, the classical split-merge algorithm was applied, and the result improved by a grouping algorithm. [ Result ] The 600 cases of samples are tested, the accuracy rate is 88%. [ Conclusion] Experiments showed that it is capable of detect and locate frontview face（s） which is（are） big and clear enough.