| Hybrid SVM／HMM Method for Face Recognition |
| |
| 引用本文： | 刘江华,陈佳品,程君实.Hybrid SVM／HMM Method for Face Recognition[J].东华大学学报(英文版),2004,21(1):34-38. |
| |
| 作者姓名： | 刘江华 陈佳品 程君实 |
| |
| 作者单位： | InformationStorageResearchCenter,ShanghaiJiaotongUniversity,Shanghai,200030 |
| |
| 基金项目： | This project is supported by the National Natural Science Foundation of China (No. 69889050) |
| |
| 摘 要： | A face recognition system based on Support Vector Machine(SVM) and Hidden Markov Model (HMM) has been proposed. The powerful discriminative ability of SVM is combined with the temporal modeling ability of HMM. The output of SVM is moderated to be probability output, which replaces the Mixture of Gauss (MOG) in HMM. Wavelet transformation is used to extract observation vector, which reduces the data dimension and improves the robustness.The hybrid system is compared with pure HMM face recognition method based on ORL face database and Yale face database. Experiments results show that the hybrid method has better performance.
|
| 关 键 词： | 人脸识别 支持向量机 隐藏马尔可夫模型 微波变换 HMM SVM |
Hybrid SVM/HMM Method for Face Recognition |
| |
| LIU Jiang-hua,CHEN Jia-pin CHENG Jun-shi Information Storage Research Center,Shanghai Jiaotong University,Shanghai.Hybrid SVM/HMM Method for Face Recognition[J].Journal of Donghua University,2004,21(1):34-38. |
| |
| Authors: | LIU Jiang-hua CHEN Jia-pin CHENG Jun-shi Information Storage Research Center Shanghai Jiaotong University Shanghai |
| |
| Institution: | Information Storage Research Center, Shanghai J iaotong University, Shanghai, 200030 |
| |
| Abstract: | A face recognition system based on Support Vector Machine (SVM) and Hidden Markov Model (HMM) has been proposed. The powerful discriminative ability of SVM is combined with the temporal modeling ability of HMM. The output of SVM is moderated to be probability output, which replaces the Mixture of Gauss (MOG) in HMM. Wavelet transformation is used to extract observation vector, which reduces the data dimension and improves the robustness. The hybrid system is compared with pure HMM face recognition method based on ORL face database and Yale face database. Experiments results show that the hybrid method has better performance. |
| |
| Keywords: | SVM HMM face recognition probability output wavelet transformation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
