计算机与现代化

• 图像处理 • 上一篇    下一篇

基于监督超向量编码和自适应GMM的人脸表情识别方法

  

  1. 无锡太湖学院工学院,江苏无锡214064
  • 收稿日期:2015-08-10 出版日期:2016-03-02 发布日期:2016-03-03
  • 作者简介: 李荣(1978-),女,江苏淮安人,无锡太湖学院工学院讲师,硕士,研究方向:图像处理,模式识别; 王华君(1979-),男,江苏宜兴人,讲师,硕士,研究方向:图像处理,模式识别; 徐燕华(1979-),女,江苏无锡人,讲师,硕士,研究方向:图像处理,模式识别; 孟德建(1979-),男,江苏扬州人,讲师,博士,研究方向:图像处理,移动互联感知,视频处理。
  • 基金资助:
     江苏省高校自然科学研究项目(14KJB520036)

A Face Expression Recognition Method Based on Fusion of Supervised #br#  Super-vector Encoding and Adaptive GMM Model

  1. School of Engineering, Taihu University of Wuxi, Wuxi 214064, China
  • Received:2015-08-10 Online:2016-03-02 Published:2016-03-03

摘要: 针对不同状态和光照条件下的人脸表情识别问题,提出一种基于自适应高斯混合模型(GMM)融合监督式超级向量编码算法。首先,提取重叠图像块;然后,通过自适应GMM提取每个图像块的局部描述子,将图像低维特征映射到高维空间;最后,利用有监督的超级向量编码完成人脸表情识别。在Multi-PIE和BU3D-FE多视点人脸表情数据库上的实验结果显示,本算法在Multi-PIE和BU3D-FE人脸库上的识别率可分别高达91.8%、95.6%,识别一个样本所耗时间仅为0.142 s。相比其他几种较新的算法,本算法取得了更高的识别率,且大大降低了识别所耗时间。

关键词:  , 人脸表情识别, 自适应, 高斯混合模型, 监督学习, 超级向量编码

Abstract:  Facial expression recognition under different lighting conditions and states is a challenging research. A fusion algorithm based on adaptive Gaussian Mixture Model (GMM) and supervised super-vector encoding is proposed. Firstly, the overlapping image blocks are extracted. Then, local descriptor from each block is extracted by the adaptive GMM so as to map images in low-dimensional space to high-dimensional space. Finally, supervised super-vector encoding is used to do classification training. Experimental results on the Multi-PIE and BU3D-FE multi-view facial expression databases show that the recognition accuracy of proposed algorithm can achieve 91.8% and 95.6% respectively on Multi-PIE and BU3D-FE. It takes only 0.142 seconds in identifying a sample on BU3D-FE. Proposed algorithm has higher recognition accuracy and less recognition time-consuming than several other excellent algorithms.

Key words: facial expression recognition, adaptive, Gaussian Mixture Model(GMM), supervised learning, super-vector encoding