作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2006, Vol. 32 ›› Issue (21): 44-46. doi: 10.3969/j.issn.1000-3428.2006.21.016

• 博士论文 • 上一篇    下一篇

基于Gabor小波的人脸检测

聂祥飞1,2,郭 军1   

  1. (1. 北京邮电大学模式识别实验室,北京 100876;2. 重庆三峡学院,重庆 404000)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2006-11-05 发布日期:2006-11-05

Face Detection Based on Gabor Wavelets

NIE Xiangfei1,2, GUO Jun1   

  1. (1. Pattern Recognition Lab, Beijing University of Posts and Telecommunications, Beijing 100876;2. Chongqing Three Gorges University, Chongqing 404000)
  • Received:1900-01-01 Revised:1900-01-01 Online:2006-11-05 Published:2006-11-05

摘要: 提出了一种新的正面人脸检测算法。该方法组合了Gabor小波变换、输入图像的Gabor特征分析和Bayes分类器来进行正面人脸检测。对训练集的平均脸作Gabor小波变换得到40个投影向量;通过计算输入图像和这40个投影向量间的内积来提取图像的Gabor特征向量;训练Bayes分类器来进行正面人脸检测。实验结果表明,该算法的计算效率和检测精度均优于特征脸方法。

关键词: 人脸检测, Gabor小波, Bayes分类器

Abstract: A novel method for frontal face detection is presented. The novelty of this paper comes from the integration of the Gabor transform of mean face, face feature analysis of the input image, and the Bayes classifier for frontal face detection. 40 projection vectors are got from Gabor transform of mean face. Face feature analysis is derived from a feature vector by calculating the inner products between the input image and the 40 projection vectors. The Bayes classifier is trained to detect frontal face in an image. The experimental results show that the proposed method has lower computational complexity and higher accuracy than Eigenfaces method.

Key words: Face detection, Gabor wavelets, Bayes classifier

中图分类号: