基于压缩感知的鲁棒性人脸表情识别.pdf

2015 年 第24 卷 第 2 期 计 算 机 系 统 应 用 基于压缩感知的鲁棒性人脸表情识别① 1,2 2 1,2 施徐敢 , 张石清 , 赵小明 1(浙江理工大学 机械自动控制学院, 杭州 310018) 2(台州学院 图像处理与模式识别研究所, 临海 317000) 摘 要: 为了有效提高噪声背景下的人脸表情识别性能, 提出一种基于压缩感知的鲁棒性人脸表情识别方法. 先 通过对腐蚀的测试样本表情图像进行稀疏表示, 再利用压缩感知理论寻求其最稀疏的解, 然后采用求得的最稀 疏解信息实现人脸表情的分类. 在标准的Cohn-Kanade 表情数据库的实验测试结果表明, 该方法取得的人脸表情 识别性能优于最近邻法、支持向量机以及最近邻子空间法. 可见, 该方法用于人脸表情识别, 识别效果较好, 鲁 棒性较高. 关键词: 压缩感知; 稀疏表示; 表情识别; 鲁棒性; 腐蚀 Compressed Sensing-Based Robust Facial Expression Recognition 1, 2 2 1, 2 SHI Xu-Gan , ZHANG Shi-Qing , ZHAO Xiao-Ming 1(School of Automatic Control of Mechanical, Zhejiang Sci-Tech University, Hangzhou 310018, China) 2(Institute of Image Processing and Pattern Recognition, Taizhou University, Linhai 317000, China) Abstract: In order to effectively improve the performance of facial expression recognition under the noisy background, a method of robust facial expression recognition based on compressed sensing is proposed. Firstly, the sparse representation of corrupted expression images of the identified test sample is sought, then the compressed sensing theory is used to solve its sparsest solution. Finally, according to the sparsest solution, facial expression classification is performed. Experimental results on benchmarking Cohn-Kanade database show that facial expression performance obtained by this method is better than the nearest neighbor (NN), support vector machine (SVM) and the nearest subspace (NS). Therefore, the proposed method shows both good recognition performance and high robustness on facial expression recognition tasks. Key words: compressed sensing; sparse representation; expressio