CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Shape Initialization Without Ground Truth For Face Alignment
Qin, Rizhen; Zhang, Ting
2016-03
会议名称2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
会议录名称2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
会议日期20-25 March 2016
会议地点Shanghai, China
摘要      The shape initialization is a crucial step for face alignment. In the literature, many approaches use the ground truth points to compute the bounding box. However, it is not always possible to detect an accurate bounding box in real applications due to various adverse factors. In this work, an effective initialization approach for face alignment is proposed. Firstly a modified Deformable Part Models (DPM) is used to estimate the face pose and the bounding box to obtain an initial shape. Then by detecting the two pupils, the roll rotation of the face is measured to correct the initial shape. To further increase the robustness and accuracy of face alignment, multiple initial shapes for each face are generated, then each one is refined by a cascade regression-based approach and we can get multiple shape estimations. Finally a better final shape is obtained by fusing the multiple estimations via the structured SVM learning. Experiments on challenging datasets and comparison with the state-of-the-art methods validate our proposed method in unconstrained environment.
关键词Shape Initialization Face Alignment Dpm Multiple Initial Shapes Structured Svm
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11493
专题模式识别国家重点实验室_机器人视觉
通讯作者Qin, Rizhen
作者单位Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Qin, Rizhen,Zhang, Ting. Shape Initialization Without Ground Truth For Face Alignment[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
SHAPE INITIALIZATION(889KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Qin, Rizhen]的文章
[Zhang, Ting]的文章
百度学术
百度学术中相似的文章
[Qin, Rizhen]的文章
[Zhang, Ting]的文章
必应学术
必应学术中相似的文章
[Qin, Rizhen]的文章
[Zhang, Ting]的文章
相关权益政策
暂无数据
收藏/分享
文件名: SHAPE INITIALIZATION WITHOUT GROUND TRUTH FOR FACE ALIGNMENT.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。