Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2008, Vol. 34 ›› Issue (19): 209-211. doi: 10.3969/j.issn.1000-3428.2008.19.071

• Artificial Intelligence and Recognition Technology • Previous Articles     Next Articles

Face Detection Method Based on Skin Model and Regional Feature

ZHANG Li-gang, HE Dong-jian   

  1. (College of Information Engineering, Northwest A&F University, Yangling 712100)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-10-05 Published:2008-10-05

基于肤色模型和区域特征的人脸检测方法

张立刚,何东健   

  1. (西北农林科技大学信息工程学院,杨凌 712100)

Abstract: Precision and speed are two appraisal criterions of face detection system. In order to get accurate precision and fast speed, this paper presents a novel method based on skin model and regional feature. This method extracts face pixels using skin model, then gets the face region through an extension method of mosaic, extracts the lip and eyes utilizing the built models and locates the central points based on the regional feature. Experiments show that the method performs easily and locates points accurately.

Key words: face detection, skin model, mosaic method, regional features

摘要: 精度和速度是人脸检测系统的两个衡量标准。针对传统人脸检测方法两者不能兼优的问题,该文提出一种结合颜色空间和特征区域的人脸检测方法。该方法采用肤色模型提取肤色像素,利用拓展的马赛克方法获取人脸区域,构建模型并提取嘴唇和眼睛,结合区域特征定位中心点。实验结果表明,该方法简单易行、定位精确。

关键词: 人脸检测, 肤色模型, 马赛克方法, 区域特征

CLC Number: