计算机与现代化 ›› 2011, Vol. 1 ›› Issue (1): 121-3.doi: 10.3969/j.issn.1006-2475.2011.01.035

• 图像处理 • 上一篇    下一篇

一种基于FKT算法的人脸表情识别方法

邱 伟   

  1. 东南大学学习科学研究中心,江苏 南京 210096
  • 收稿日期:2010-09-13 修回日期:1900-01-01 出版日期:2011-01-20 发布日期:2011-01-20

A Method of Facial Expression Recognition Based on FKT Algorithm

QIU Wei   

  1. Research Center for Learning Science, Southeast University, Nanjing 210096, China
  • Received:2010-09-13 Revised:1900-01-01 Online:2011-01-20 Published:2011-01-20

摘要:

人脸表情识别是模式识别和计算机视觉领域的重要课题之一。本文使用C++编程实现基于动态级联算法的人脸检测器,使用人脸检测器提取出表情识别需要的人脸数据集,通过FKT(FukunagaKoontz Transform)算法来解决表情识别问题。实验结果表明算法的有效性。

关键词: 人脸表情识别, 人脸检测, 动态级联, FKT算法

Abstract:

Facial expression recognition has been one of the important research themes in the fields of pattern recognition and computer vision. In this paper, a face detection system based on the dynamic cascade learning algorithm is implemented by C++ programs. With the help of the obtained face detector, face samples are extracted to form the data sets for expression recognition. Finally, FKT (FukunagaKoontz Transform) algorithm is applied to solve the problem of expression recognition. The experimental results demonstrate the effectiveness of the proposed method.

Key words: facial expression recognition, face detection, dynamic cascade, FKT algorithm