上海大学学报(自然科学版)

• 计算机工程与科学 • 上一篇    下一篇

基于聚类肤色模型的人脸检测

丁友东1,杜晓凤2,李晓强1   

  1. 1.上海大学 计算机工程与科学学院,上海 20072; 2.厦门大学 计算机科学系,厦门 361005
  • 收稿日期:2007-03-28 修回日期:1900-01-01 出版日期:2007-10-20 发布日期:2007-10-20
  • 通讯作者: 丁友东

Human Face Detection Based on Cluster Skin Color Model

DING You-dong1,DU Xiao-feng2,Li Xiao-qiang1   

  1. 1. School of Computer Engineering and Science, Shanghai University, Shanghai 200072, China;
    2. Department of Computer Science, Xiamen University, Xiamen 361005, China
  • Received:2007-03-28 Revised:1900-01-01 Online:2007-10-20 Published:2007-10-20
  • Contact: DING You-dong1

摘要: 在安全检测、人机交互等人脸识别应用中,人脸的检测与定位是前期重要工作.该文提出一种改进的基于亮度聚类的肤色模型,并提出一种新的最佳阈值选择算法,设计了肤色检测算法流程.实验证明该算法提高了人脸检测的速度和鲁棒性.

关键词: 肤色模型, 聚类, 人脸检测

Abstract: Human face localization and detection is often the first step in applications such as video surveillance and human-computer interface. In this paper,a skin color model based on cluster and a novel selection method of best limitvalue is presented. An algorithmic flow for human face skin color detection is proposed. Examples are given to show the improved detection speed of the proposed algorithm and its robustness.

Key words: cluster, skin model, face detection