Real-time multiview face detection and pose estimation based on cost-sensitive AdaBoost | |
Ma Yong ; Ding Xiaoqing | |
2010-05-06 ; 2010-05-06 | |
关键词 | Theoretical or Mathematical/ algorithm theory face recognition feature extraction generalisation (artificial intelligence) position measurement real-time systems/ pose estimation real-time multiview face detection AdaBoost algorithm cost-sensitivity multiview faces simple-to-complex based detector architecture coarse-to-fine view-based detector architecture face detector nonface detector/ B6135E Image recognition B7320C Spatial variables measurement C5260B Computer vision and image processing techniques C1230 Artificial intelligence |
中文摘要 | Locating multiview faces in images with a complex background remains a challenging problem. In this paper, an integrated method for real-time multi-view face detection and pose estimation is presented. A simple-to-complex and coarse-to-fine view-based detector architecture has been designed to detect multi-view faces and estimate their poses efficiently. Both the pose estimators and the view-based face/nonface detectors are trained by a cost-sensitive AdaBoost algorithm to improve the generalization ability. Experimental results show that the proposed multi-view face detector, which can be constructed easily, gives more robust face detection and pose estimation and has a faster real-time detection speed compared with other conventional methods. |
语种 | 英语 ; 英语 |
出版者 | Editorial Board of J. of Tsinghua University ; China |
内容类型 | 期刊论文 |
源URL | [http://hdl.handle.net/123456789/11292] ![]() |
专题 | 清华大学 |
推荐引用方式 GB/T 7714 | Ma Yong,Ding Xiaoqing. Real-time multiview face detection and pose estimation based on cost-sensitive AdaBoost[J],2010, 2010. |
APA | Ma Yong,&Ding Xiaoqing.(2010).Real-time multiview face detection and pose estimation based on cost-sensitive AdaBoost.. |
MLA | Ma Yong,et al."Real-time multiview face detection and pose estimation based on cost-sensitive AdaBoost".(2010). |
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