期刊文献+

肤色相似度和动态阈值相结合的肤色分割技术 被引量:10

Skin segmentation using similarity of skin color and dynamic threshold
下载PDF
导出
摘要 为了提高人脸检测的速度与性能,提出一种基于肤色相似度与动态阈值相结合的肤色分割方法。首先在YCgCr颜色空间计算肤色相似度,然后给出一种基于类间方差和类内离散度相结合的动态阈值确定方法,根据求得的动态阈值进行肤色分割,并对肤色分割后的二值图像进行滤除噪声处理。实验结果表明该方法改善了肤色分割性能,能够在复杂背景下实现肤色区域的精确分割,从而提高了人脸检测的速度和性能。 A method for skin segmentation based on similarity of skin color and dynamic threshold is proposed to improve the speed and performance of face detection.Firstly, the similarity of skin color is calculated in YCgCr space.Then, the method based on between-cluster variance and within-class scatter for selecting the threshold dynamically is proposed.Skin color segmentation is implemented according to the dynamic threshold.The binary image obtained by skin segmentation is processed in order to elimi- nate noise.The experimental results show that the proposed algorithm improves the performance of skin segmentation,and can seg- ment skin regions exactly in the complex background so as to improve the speed and performance of face detection.
出处 《计算机工程与应用》 CSCD 北大核心 2010年第18期1-3,12,共4页 Computer Engineering and Applications
基金 国家高技术研究发展计划(863)No.2006AA04Z259 中国博士后基金资助项目No.20060400809 中央高校基本科研业务费专项资金资助项目No.HEUCF100606 国家教育部博士点专项基金资助No.20092304120013~~
关键词 人脸检测 肤色分割 肤色相似度 阈值分割 动态阈值确定 face detection skin segmentation similarity of skin color threshold segmentation dynamic threshold selecting
  • 相关文献

参考文献11

  • 1梁路宏,艾海舟,徐光祐,张钹.人脸检测研究综述[J].计算机学报,2002,25(5):449-458. 被引量:355
  • 2Tie Y,Guan L.Automatic face detection in video sequences using local normalization and optimal adaptive correlation techniques[J]. Pattern Recognition,2009,42:1859-1868.
  • 3Zhang Q S,Kamata S I,Zhang J.Face detection and tracking in color images using color centroids segmentation[C]//IEEE International Conference on Robotics and Biomimetics,Bangkok,Thailand, February 21-26,2009.United States: IEEE Computer Society, 2009 : 1008-1013.
  • 4Yang U,Kim B,and Sohn K.Illumination invafiant skin color segmentation[C]//4th IEEE Conference on Industrial Electronics and Applications,Xi'an,China,May 25-27,2009.United States:IEEE Computer Society, 2009: 636-641.
  • 5Li B,Xue X Y,Fan J P.A robust incremental learning framework for accurate skin region segmentation in color images[J].The Journal of the Pattern Recognition Socirty,2007,40: 3621-3632.
  • 6Chen H Y,Huang C L,Fu C M.Hybrid-boost learning for multipose face detection and facial expression recognition[J].Pattem Recognition, 2008,41 : 1173-1185.
  • 7Terrillon J C,Shirazi M N,Fukamachi H.Comparative performance of different skin chrominance models and chrominanee spaces for the automatic detection of human faces in color images[C]//Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition,Grenoble,France,March 28-30 2000.US- A:IEEE Comput Soc,2000:54-61.
  • 8de Dios J J,Garcia N.Face detection based on a new color space yCgCr[C]//IEEE International Conference on Image Processing,Barcelona, Spain,Sept 14-17 2003.Piscataway,NJ,USA:IEEE,2003:909-912.
  • 9付忠良.图象阈值选取方法的构造[J].中国图象图形学报(A辑),2000,5(6):466-469. 被引量:80
  • 10付忠良.基于图像差距度量的阈值选取方法[J].计算机研究与发展,2001,38(5):563-567. 被引量:41

二级参考文献93

共引文献471

同被引文献85

引证文献10

二级引证文献20

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部