Classification-Based Face Detection Using Compound Features

详细信息    查看全文

• 作者：Linlin Huang ; Akinobu Shimizu ; Hidefumi Kobatake
• 刊名：Lecture Notes in Computer Science
• 出版年：2005
• 出版时间：2005
• 年：2005
• 卷：3497
• 期：1
• 页码：p.99
• 全文大小：182 KB
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

In this paper, we propose a classification-based face detection method using compound features. Four kinds of features, namely, intensity, Gabor filter feature, decomposed gradient feature, and Harr wavelet feature are combined to construct a compound feature vector. The projection of the feature vector on a reduced feature subspace learned by principal component analysis (PCA) is used as the input of the underlying classifier, which is a polynomial neural network (PNN). The experimental results on testing a large number of images demonstrate the effectiveness of the proposed method.