Incremental learning patch-based bag of facial words representation for face recognition in videos
文献类型：期刊论文
| ; | |
| 作者 | Chao Wang ; Yunhong Wang; Zhaoxiang Zhang; Yiding Wang
|
| 刊名 | Multimedia Tools and Applications
 ; Multimedia Tools and Applications
|
| 出版日期 | 2014-10-17 ; 2014-10-17 |
| 卷号 | 72期号:3页码:2439-2467 |
| 关键词 | Video Analysis Video Analysis Face Recognition Face Recognition Biometrics Incremental Learning Biometrics Incremental Learning Bag Of Words Bag Of Words |
| 英文摘要 | Video-based face recognition is a fundamental topic in image processing and video analysis, and presents various challenges and opportunities. In this paper, we introduce an incremental learning approach to video-based face recognition which efficiently exploits the spatiotemporal information in videos. Face image sequences are incrementally clustered based on their descriptors, and the representative face images of each cluster are picked out. The incremental algorithm of creating facial visual words is applied to construct a codebook using the descriptors of the representative face images. Continuously, with the quantization of the facial visual words, each descriptor extracted from patches is converted into codes, and codes from each region are pooled together into a histogram. The representation of the face image is generated by concatenating the histograms from all regions, which is employed to perform the categorization. In the online recognition, a similarity score matrix and a voting algorithm are employed to judge a face video’s identity. Recognition is performed online while face video sequence is continuous and the proposed method gives nearly realtime feedback. The proposed method achieves a 100 % verification rate on the Honda/UCSD database and 82 % on the YouTube datebase. Experimental results demonstrate the effectiveness and flexibility of the proposed method.; Video-based face recognition is a fundamental topic in image processing and video analysis, and presents various challenges and opportunities. In this paper, we introduce an incremental learning approach to video-based face recognition which efficiently exploits the spatiotemporal information in videos. Face image sequences are incrementally clustered based on their descriptors, and the representative face images of each cluster are picked out. The incremental algorithm of creating facial visual words is applied to construct a codebook using the descriptors of the representative face images. Continuously, with the quantization of the facial visual words, each descriptor extracted from patches is converted into codes, and codes from each region are pooled together into a histogram. The representation of the face image is generated by concatenating the histograms from all regions, which is employed to perform the categorization. In the online recognition, a similarity score matrix and a voting algorithm are employed to judge a face video’s identity. Recognition is performed online while face video sequence is continuous and the proposed method gives nearly realtime feedback. The proposed method achieves a 100 % verification rate on the Honda/UCSD database and 82 % on the YouTube datebase. Experimental results demonstrate the effectiveness and flexibility of the proposed method. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/13217]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Zhaoxiang Zhang |
| 推荐引用方式 GB/T 7714 | Chao Wang,Yunhong Wang,Zhaoxiang Zhang,et al. Incremental learning patch-based bag of facial words representation for face recognition in videos, Incremental learning patch-based bag of facial words representation for face recognition in videos[J]. Multimedia Tools and Applications, Multimedia Tools and Applications,2014, 2014,72, 72(3):2439-2467, 2439-2467. |
| APA | Chao Wang,Yunhong Wang,Zhaoxiang Zhang,&Yiding Wang.(2014).Incremental learning patch-based bag of facial words representation for face recognition in videos.Multimedia Tools and Applications,72(3),2439-2467. |
| MLA | Chao Wang,et al."Incremental learning patch-based bag of facial words representation for face recognition in videos".Multimedia Tools and Applications 72.3(2014):2439-2467. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。