基于双眼独立动态阈值人脸预处理及识别.pdfVIP

ISSN1009-3044 E-mail: eduf@ Computer Knowledge and Technology 电脑知识与技术 第8 卷第7 期 (2012 年3 月) Computer Knowledge and Technology 电脑知识与技术 Vol.8, No.7, March 2012. Tel:+86-551-5690963 5690964 基于双眼独立动态阈值的人脸预处理及识别 方超,王斌斌，陈立生 （厦门大学计算机系，福建厦门361005） 摘要：针对实际环境中采集的人脸图像预处理问题，提出双眼独立动态阈值方法定位双眼。先划分左右眼大致区域，再采用区域像 素点百分比选取灰度值当作二值化的阈值。提取左右眼候选位置后，结合人眼位置的一些判别准则进行最终定位。截取双眼间条 状区域，应用灰度累积直方图方法，定位鼻子与嘴巴区域。在ORL 库和essex94 数据库上比较了区域划分前后的识别效果，实验结 果表明采用所提出的预处理方法后，识别效果有比较明显的提升。 关键词：人脸识别；人眼定位；动态阈值；灰度累计直方图；LBP 算子 中图分类号：TP18 文献标识码：A 文章编号：1009-3044(2012)07-1618-04 Eyes-independentDynamicThresholdBasedHumanFacesPreprocessingandRecognition FANG Chao, WANG Bin-bin, CHEN Li-sheng (Department of Computer Science, Xiamen University, Xiamen 361005, China) Abstract: Based on eyes-independent dynamic threshold, this paper proposes a preprocessing method for human face images collected from real environment. First carves out the approximate area of the left and right eye, and then calculates the gray value from the percent⁃ age of region pixels, selects the calculated value as the binarization threshold. After exacting candidate locations of left and right eyes, com⁃ bined with the eye position criterion the both eyes can be finally located. Locate the region of nose and mouth by applying grayscale cumu⁃ lative histogram method based on the striped areas between eyes. Compare the recognition results before and after zoning human face in ORL face database and excess94 face database, the results show that the proposed preprocessing method can significantly improved the ef⁃ fect of identify. Keywords:face recognition; localization of human eyes; dynamic threshold; grayscale cumulative histogram; LBP operator 人脸识别是模式识别的一个重要领域，也是目前的一个研究热点。人脸识别在安防，管理，金融等领域都有巨大的应用前景。 同时