首页 | 本学科首页   官方微博 | 高级检索  
     

基于改进最大熵法的复杂背景肤色检测
引用本文:徐静云,刘晓红,王举辉. 基于改进最大熵法的复杂背景肤色检测[J]. 山东理工大学学报:自然科学版, 2007, 21(4): 78-80
作者姓名:徐静云  刘晓红  王举辉
作者单位:山东理工大学,计算机科学与技术学院,山东,淄博,255049;山东理工大学,计算机科学与技术学院,山东,淄博,255049;山东理工大学,计算机科学与技术学院,山东,淄博,255049
摘    要:肤色检测是人脸检测的重要组成部分,特别是在复杂背景下,快速准确找到肤色是一个难点.在做肤色检测中首先通过对彩色图片进行自适应光照补偿,再采用改进的YCbCr色彩空间,建立肤色高斯模型,然后利用基于改进最大熵算法进行人脸肤色检测,之后进行形态学去噪处理.实验证明,该方法能有效地从复杂背景中检测出人脸肤色.

关 键 词:光照补偿  非线性色彩空间  高斯模型  最大熵
文章编号:1672-6197(2007)04-0078-03
修稿时间:2006-10-10

Skin location based on improved maximum entropy under complex background
XU Jing-Yun,LIU Xiao-Hong,WANG Ju-Hui. Skin location based on improved maximum entropy under complex background[J]. Journal of Shandong University of Technology:Science and Technology, 2007, 21(4): 78-80
Authors:XU Jing-Yun  LIU Xiao-Hong  WANG Ju-Hui
Affiliation:School of Computer Science and Engineering, Shandong University of Technology, Zibo 255049, China
Abstract:The detection and location of skin is the important constituent in face detection especially under the complex background,it is a hot and difficult point to search for a way to locate the skin fastly and accurately.The paper carries on the auto-adapted illumination compensation for color picture,establishes a face Gauss model and makes use of the Improved Maximum Entropy to carry out skin detection.The experimental results show that the proposed approach is effective to detect human skin in any background.
Keywords:illumination compensation  non-linear color space  skin gauss model  maximum entropy
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