部分遮挡人脸的检测技术分析  

Analysis of Detection on Partially Occluded Face

作　　者：杜杏菁[1] 于咏霞[1] 刘春梅[1] 

机构地区：[1]华北科技学院计算机系,北京东燕郊101601

出　　处：《华北科技学院学报》2009年第1期62-65,共4页Journal of North China Institute of Science and Technology

摘　　要：生物识别技术是计算机技术的一个新的应用领域,人脸识别成为生物识别中的一个热点问题,人脸检测是人脸识别的前期重要工作部分。现有的人脸检测算法多是针对简单背景下只有一个人脸的图像进行的,对部分遮挡人脸的检测很少研究。文中提出局部遮挡人脸恢复的属性关系图方法。通过对较复杂背景下10幅图像实验(包括遮挡人脸和非遮挡人脸),该算法对非遮挡人脸的正确检测率为98%,对遮挡人脸的准确检出率为62%。该算法对部分遮挡人脸的检测有一定的指导意义,但需要进一步的实验和提高准确检出率。As a new field of information technology, biometrics recognition consists of the recognition of face, iris, retina, pronunciation etc. In recent years, Static face detection algorithms concerning the categories of detection technology have been raised, but these algorithms put their focus on the detection of clear face. The research of detection on partially occluded face has not yet been conducted. Under this circumstance, the thesis gives a brand new static detection and dynamic track algorithm. By analyzing the 10 graphs, it has been found that the detection accuracy of the partially occluded faces is 62% and the clear nonoccluded faces detection accuracy is 98%. This new algorithm can provide important reference to partial face detection, however, the algorithm still needs to be verifed and improved further.

关 键 词：人脸检测 肤色模型 知识模型 

分 类 号：TD335.3[矿业工程—矿井建设]