首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于皮肤探测的自动对焦
引用本文:田宜彬,徐之海,冯华君,戴瑞春,戴顺林,李奇,边美娟.基于皮肤探测的自动对焦[J].光子学报,2003,32(1):56-60.
作者姓名:田宜彬  徐之海  冯华君  戴瑞春  戴顺林  李奇  边美娟
作者单位:1. 浙江大学现代光学仪器国家重点实验室,杭州,310027;Department of Vision Science,University of California,Berkeley,CA 94720,USA
2. 浙江大学现代光学仪器国家重点实验室,杭州,310027
3. 中兴通信有限公司上海第一研究所,上海,200231
基金项目:FundedbythePlanforCadreCollegeTeachersoftheMinistryofEducationofP .R .China
摘    要:用模式识别方法选择对焦窗口,对成像主体是人的情况进行了详细讨论.先对自动对焦中使用模式识别的必要性进行了深入的理论分析,然后讨论了具体的实现方法.利用人类皮肤颜色分布的特点来探测图像中的皮肤区域;用形态学操作来去除皮肤区域中的眼睛、鼻孔、嘴巴和其他非皮肤碎片;最后以所得的皮肤区域作为对焦窗口应用对焦评价函数.实验结果表明这种方法的实用性和有效性.

关 键 词:自动对焦  对焦评价函数  成像主体  背景  对焦窗口  皮肤探测
收稿时间:2001-12-17

Auto-focus Based on Skin Detection
Abstract.Auto-focus Based on Skin Detection[J].Acta Photonica Sinica,2003,32(1):56-60.
Authors:Abstract
Institution:1. National Lab of Modern Optical Instrument, Zhejiang University, Hangzhou 310027;2. Shanghai No.1 Research Institute, Zhongxing Telecom, Shanghai 200231, China;3. Department of Vision Science, University of California, Berkeley, CA 94720, USA
Abstract:Using pattern recognition to select focus windows, the primary imaging objects which are men (PIOM for short) is discussed in details. The necessity of utilizing pattern recognition in auto- focus is illustrated. The skin-color distribution characteristics are used to detect skin regions in PIOM images. Morphological operations are employed in the process to get ride of interspaces arising from eyes, nostrils, mouths and other non-skin parts among skin areas. Then the detected skin regions are chosen as the focus windows. Experimental results show the realistic applicability and efficiency of this approach.
Keywords:Auto-focus  Focus measure  Primary imaging object  Focus window  Skin detection
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《光子学报》浏览原始摘要信息
点击此处可从《光子学报》下载免费的PDF全文
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