| 基于鉴别字典学习的遮挡人脸姿态识别 |
| |
| 引用本文： | 邱益鸣,廖海斌,陈庆虎.基于鉴别字典学习的遮挡人脸姿态识别[J].武汉大学学报(信息科学版),2018,43(2):275. |
| |
| 作者姓名： | 邱益鸣 廖海斌 陈庆虎 |
| |
| 作者单位： | 1.武汉大学电子信息学院, 湖北 武汉, 430072 |
| |
| 基金项目： | 湖北省自然科学基金2017CFB300湖北省教育厅科学技术研究项目Q20172805湖北省教育科学规划项目2016GB086 |
| |
| 摘 要： | 利用字典学习与稀疏表示的信号重建与分类的性能，两步字典训练学习方法引入到鲁棒性人脸姿态识别中。首先，将人脸姿态离散化为不同的子空间，使用K-奇异值分解法（K-SVD）为每个子空间训练一个子字典使其对应一个类别；然后，将所有子字典组合成超完备字典；最后，采用基于Gabor特征与稀疏表示的方法进行姿态分类。为了提高字典的分类能力，本文采用两步字典训练学习方法，并在第二步学习中加入类别约束；为了提高算法的鲁棒性，本文重构一个遮挡人脸字典，解决人脸姿态识别中人脸遮挡问题。通过在公开的XJTU、PIE和CAS-PEAL-R1人脸库上的实验结果表明，本文方法在具有光照、噪声和遮挡变化的人脸库识别率均能达到95%左右，基本能达到实际应用的要求。
|
| 关 键 词： | 人脸姿态识别 人脸识别 遮挡人脸处理 字典学习 稀疏表示 |
| 收稿时间： | 2016-03-29 |
Occluded Face Pose Recognition Based on Dictionary Learning with Discrimination Performance |
| |
| Affiliation: | 1.School of Electronic Information, Wuhan University, Wuhan 430072, China2.School of Computer Science and Technology, Hubei University of Science and Technology, Xianning 437100, China3.Jiangsu Jinling Sci & Tech Group Co., Ltd, Nanjing 210008, China |
| |
| Abstract: | This paper make full use of dictionary learning and sparse representation for signal reconstruction and classification, and present a two-step dictionary learning method and apply it to robust face pose recognition. The proposed approach models the appearance of face images from the subspace via K-SVD that learns the sub-dictionary from a set of images. A combination of the trained sub-dictionaries of all pose classes are used as an over-complete dictionary. Finally, the Gabor features are extracted for sparse representation and classification. In order to improve the classification ability, we put forward a two-step dictionary learning method, and carry out dictionary learning with label constraints in the second step. Additionally, in order to improve robustness against face occlusion, we introduce a pose occlusion dictionary to code the occluded portions of face images. Several experiments were performed on XJTU, PIE, and CAS-PEAL-R1 databases. Recognition results show that the proposed method can achieve a recognition rate of about 95% under illumination, noise, and occlusion variations. It can satisfy the requirements of practical applications. |
| |
| Keywords: | |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《武汉大学学报(信息科学版)》浏览原始摘要信息 |
|
点击此处可从《武汉大学学报(信息科学版)》下载全文 |
|
