首页 | 本学科首页   官方微博 | 高级检索  
     

复杂背景下人眼自动定位
引用本文:陶亮,庄镇泉.复杂背景下人眼自动定位[J].计算机辅助设计与图形学学报,2003,15(1):38-42.
作者姓名:陶亮  庄镇泉
作者单位:1. 中国科学技术大学电子科学与技术系,合肥,230026;安徽大学电子工程与信息科学系,合肥,230039
2. 中国科学技术大学电子科学与技术系,合肥,230026
基金项目:教育部高等学校博士点专项科研基金(19990 35 80 8),安徽省自然科学基金(0 10 42 2 10 ),安徽省教育厅自然科学重点研究项目(2 0 0 1kj0 2 0zd)资助
摘    要:针对复杂背景下静态人脸灰度图像,提出一种人眼自动定位方法。首先基于人脸几何特征先验知识,建立人眼位置的判定准则,对分割阈值范围进行粗估计;然后采用分割阈值递增法,并结合人眼位置判定准则,判定分割图像中双眼黑块是否出现;最后利用二维相关系数作为对称相似性测度,检验检测出的双眼黑块的真实性。

关 键 词:复杂背景  人眼自动定位  人脸识别  模式识别  人工智能  分割阈值递增法  直方图平滑处理  计算机
修稿时间:2001年10月26

Locating Human Eyes in Complex Background
Tao Liang , Zhuang Zhenquan.Locating Human Eyes in Complex Background[J].Journal of Computer-Aided Design & Computer Graphics,2003,15(1):38-42.
Authors:Tao Liang  Zhuang Zhenquan
Affiliation:Tao Liang 1,2) Zhuang Zhenquan 1) 1)
Abstract:Based on geometrical facial features and thresholding, this paper presents a novel method for automatically locating human eyes in grayscale still images with complex background. A determination criterion of eye location is established by the priori knowledge of geometrical facial features. A range of threshold values that would separate eye blocks from others in a segmented facial image is estimated from the facial image histogram. With the progressive increase of the threshold by an appropriate step in that range, the size of existing blocks in the segmented facial image will expand, some existing blocks will merge into one block, and some new blocks will emerge. Once two eye blocks appear from the segmented image, they will be detected by the determination criterion of eye location. A 2 D correlation coefficient is used as a symmetry similarity measure to check the truth of detected eyes.
Keywords:localization of human eyes  threshold values  face recognition
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号