CASIA OpenIR  > 智能感知与计算研究中心
Dynamic Feature Matching for Partial Face Recognition
He LX(何凌霄); Li HQ(李海青); Zhang Q(张琪); Sun ZN(孙哲南)
Source PublicationIEEE Transactions on Image Processing
2019
Issue2Pages:791-802
Abstract

Partial face recognition (PFR) in an unconstrained environment is a very important task, especially in situations where partial face images are likely to be captured due to occlusions, out-of-view, and large viewing angle, e.g., video surveillance and mobile devices. However, little attention has been paid to PFR so far and thus, the problem of recognizing an arbitrary patch of a face image remains largely unsolved. This study proposes a novel partial face recognition approach called Dynamic Feature Matching (DFM), which combines Fully
Convolutional Networks (FCNs) and Sparse Representation Classification (SRC) to address partial face recognition problem regardless of various face sizes. DFM does not require prior position information of partial faces against a holistic face. By sharing computation, the feature maps are calculated from the entire input image once, which yields a significant speedup. Experimental results demonstrate the effectiveness and advantages of DFM in comparison with state-of-the-art PFR methods on several partial face databases, including CAISA-NIR-Distance, CASIA-NIR-Mobile, and LFW databases. The performance of DFM is also impressive in partial person re-identification on Partial RE-ID and iLIDS databases. The source code of DFM can be found at https://github.com/lingxiao-he/dfm new.

KeywordFully Convolutional Network Dynamic Feature Matching Partial Face Recognition
Indexed BySCI
Language英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23696
Collection智能感知与计算研究中心
Corresponding AuthorSun ZN(孙哲南)
Affiliation中科院自动化研究所
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
He LX,Li HQ,Zhang Q,et al. Dynamic Feature Matching for Partial Face Recognition[J]. IEEE Transactions on Image Processing,2019(2):791-802.
APA He LX,Li HQ,Zhang Q,&Sun ZN.(2019).Dynamic Feature Matching for Partial Face Recognition.IEEE Transactions on Image Processing(2),791-802.
MLA He LX,et al."Dynamic Feature Matching for Partial Face Recognition".IEEE Transactions on Image Processing .2(2019):791-802.
Files in This Item: Download All
File Name/Size DocType Version Access License
08467369.pdf(3747KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[He LX(何凌霄)]'s Articles
[Li HQ(李海青)]'s Articles
[Zhang Q(张琪)]'s Articles
Baidu academic
Similar articles in Baidu academic
[He LX(何凌霄)]'s Articles
[Li HQ(李海青)]'s Articles
[Zhang Q(张琪)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[He LX(何凌霄)]'s Articles
[Li HQ(李海青)]'s Articles
[Zhang Q(张琪)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 08467369.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.