Landmark perturbation-based data augmentation for unconstrained face recognition | |
Lv, Jiang-Jing; Cheng, Cheng; Tian, Guo-Dong; Zhou, Xiang-Dong; Zhou, Xi | |
刊名 | SIGNAL PROCESSING-IMAGE COMMUNICATION |
2016 | |
卷号 | 47页码:465-475 |
ISSN号 | 0923-5965 |
DOI | 10.1016/j.image.2016.03.011 |
英文摘要 | Face alignment is a key component of face recognition system, and facial landmark points are widely used for face alignment by a number of face recognition systems. However, inaccurate locations of landmark points bring about spatial misalignment which degrades the performance of face recognition systems. In order to alleviate this problem, we propose a simple and efficient data augmentation approach, which uses artificial landmark perturbation to generate a huge number of misaligned face images, to train Deep Convolutional Neural Networks (DCNN) models robust to landmark misalignment. In our experiments, three types of facial landmark-based face alignment methods are applied to train DCNN models on CASIA-WebFace training database. Experimental results on Labeled Faces in the wild database (LFW) and YouTube Faces database (YTF) verify the effectiveness of our approach. (C) 2016 Elsevier B.V. All rights reserved. |
语种 | 英语 |
WOS记录号 | WOS:000385601600038 |
内容类型 | 期刊论文 |
源URL | [http://119.78.100.138/handle/2HOD01W0/4353] |
专题 | 智能安全技术研究中心 |
作者单位 | (1) Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Intelligent Multimedia Tech Res Ctr, Chongqing 400714, Peoples R China |
推荐引用方式 GB/T 7714 | Lv, Jiang-Jing,Cheng, Cheng,Tian, Guo-Dong,et al. Landmark perturbation-based data augmentation for unconstrained face recognition[J]. SIGNAL PROCESSING-IMAGE COMMUNICATION,2016,47:465-475. |
APA | Lv, Jiang-Jing,Cheng, Cheng,Tian, Guo-Dong,Zhou, Xiang-Dong,&Zhou, Xi.(2016).Landmark perturbation-based data augmentation for unconstrained face recognition.SIGNAL PROCESSING-IMAGE COMMUNICATION,47,465-475. |
MLA | Lv, Jiang-Jing,et al."Landmark perturbation-based data augmentation for unconstrained face recognition".SIGNAL PROCESSING-IMAGE COMMUNICATION 47(2016):465-475. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论