| 改进的稀疏表示静止-视频人脸识别算法 |
| |
| 引用本文： | 范哲意,曾亚军,蒋姣,刘志文. 改进的稀疏表示静止-视频人脸识别算法[J]. 信号处理, 2016, 32(5): 567-574. DOI: 10.16798/j.issn.1003-0530.2016.05.009 |
| |
| 作者姓名： | 范哲意 曾亚军 蒋姣 刘志文 |
| |
| 作者单位： | 北京理工大学信息与电子学院 |
| |
| 摘 要： | 静止-视频人脸识别是指训练集为高质量静止图像而测试集为低质量视频序列的一种身份识别技术。针对图像对齐困难和运动模糊问题，提出了一种改进的稀疏表示静止-视频人脸识别算法。根据梯度方差信息，实现了视频条件下人脸图像中几何特征的对齐。通过对图像进行多尺度滤波操作构造字典，解决了运动模糊问题。利用图像之间的互相关系数，提取了视频序列中的关键帧。实验结果表明，提出的算法较神经网络、支持向量机等方法有明显的性能改善。
|
| 关 键 词： | 静止-视频人脸识别 稀疏表示 人脸对齐 运动模糊 关键帧 |
| 收稿时间： | 2015-08-27 |
Improved Still-to-Video Face Recognition Algorithm Based on Sparse Representation |
| |
| Affiliation: | School of Information and Electronics, Beijing Institute of Technology |
| |
| Abstract: | Still-to-Video face recognition is an identification technology, whose gallery contains still face images and the query is a video with low quality. With the purpose of overcoming the difficulties of face alignment and motion blur, this paper proposed an improved approach for face recognition in videos based on sparse representation. According to the gradient variance, the proposed approach enabled face alignment in videos. Moreover, motion blur was solved by the dictionary which was constructed by multi-scale filtering. Further, using the cross correlation coefficient between frames, key-frames in video sequences were selected. Experimental results show that the proposed approach outperforms other several approaches, such as neural networks and support vector machines. |
| |
| Keywords: | |
|
| 点击此处可从《信号处理》浏览原始摘要信息 |
|
点击此处可从《信号处理》下载免费的PDF全文 |
|
