计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (18): 173-175.

• 图形、图像、模式识别 • 上一篇    下一篇

较强光照下肤色结合发色检测人脸的方法研究

黄亦佳,潘 巍   

  1. 首都师范大学 信息工程学院,北京100048
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-06-21 发布日期:2011-06-21

Research of face detection by skin color with hair color under strong light condition

HUANG Yijia,PAN Wei   

  1. Institute of Information Engineering,Capital Normal University,Beijing 100048,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-06-21 Published:2011-06-21

摘要: 研究了基于不同颜色空间的人脸检测算法,并在此基础上针对较强光照条件下或肤色与背景色比较接近时检测算法可能会将人脸检测为背景的情况,提出了一种新的基于肤色和发色的人脸检测自适应算法。实验结果表明,即使在较强光照条件下或肤色与背景比较接近时,该算法一样能准确地检测到正面或略有倾斜的人脸。

关键词: 人脸检测, 肤色模型, 发色模型

Abstract: This paper discusses face detection algorithms based on different color spaces,and then provides a new adaptive face detection algorithm based on both face-color and hair-color space.Experimental results show that even under the strong light conditions,or the background color and face color is similar,the algorithm also can accurately detect a front or slightly sloping of the face.

Key words: face detection, skin color model, hair color model