检索
E-mail
RSS
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 ›› 2009, Vol. 35 ›› Issue (19): 195-197.doi: 10.3969/j.issn.1000-3428.2009.19.065

• 人工智能及识别技术 • 上一篇    下一篇

基于新Haar-like特征的多角度人脸检测

刘晓克，孙燮华，周永霞   

  1. (中国计量学院信息工程学院，杭州 310018)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-10-05 发布日期:2009-10-05

Multi-angle Face Detection Based on New Haar-like Feature

LIU Xiao-ke, SUN Xie-hua, ZHOU Yong-xia   

  1. (College of Information Engineering, China Jiliang University, Hangzhou 310018)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-10-05 Published:2009-10-05

PDF

4558

被引次数

40 | 4

摘要： 在Haar-like特征的基础上增加新的检测特征，给出特征计算方法和积分方法，实现多角度人脸检测。将多角度人脸分为3类，即全侧脸、半侧脸和正面人脸。利用连续Adaboost算法训练各类人脸检测器，用金字塔式结构将各类人脸检测器级联成一个多角度人脸检测器。在CMU人脸检测集合上，该检测器的成功率为85.2%，高于Adaboost算法和浮点Adaboost算法。

关键词: Haar-like特征, 特征计算, 连续Adaboost算法, 金字塔式结构

Abstract: This paper adds some new detection features on the basis of Haar-like feature, gives the feature calculation method and integration method, and achieves multi-angle face detection. It divides multi-angle face into three categories: all side face, half side face and positive face. Continuous Adaboost algorithm is used to train various types of face detector. It cascades various types of face detectors into a multi-angle face detector by using pyramid-style structure. In CMU face detection aggregation, the success rate of this detector is 85.2% which is higher than that of Adaboost algorithm and float Adaboost algorithm.

Key words: Haar-like feature, feature calculation, continuous Adaboost algorithm, pyramid-style structure

中图分类号: