Cascaded Regressions of Learning Features for Face Alignment

被引：0

作者：

Ngoc-Trung Tran ^{[1
,2
]}

Ababsa, Fakhreddine ^{[2
]}

Ben Fredj, Sarra ^{[3
]}

Charbit, Maurice ^{[1
]}

机构：

[1] Telecom ParisTECH, CNRS, LTCI, 37-39 Rue Dareau, F-75014 Paris, France

[2] Univ Evry, IBISC, F-91020 Evry, France

[3] Observ Paris, UFE, F-92195 Meudon, France

来源：

ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, ACIVS 2015 | 2015年 / 9386卷

关键词：

Face alignment; Cascaded regression; Face tracking; Learning feature; MODEL;

D O I：

10.1007/978-3-319-25903-1_61

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Face alignment is a fundamental problem in computer vision to localize the landmarks of eyes, nose or mouth in 2D images. In this paper, our method for face alignment integrates three aspects not seen in previous approaches: First, learning local descriptors using Restricted Boltzmann Machine (RBM) to model the local appearance of each facial points independently. Second, proposing the coarse-to-fine regression to localize the landmarks after the estimation of the shape configuration via global regression. Third, and using synthetic data as training data to enable our approach to work better with the profile view, and to forego the need of increasing the number of annotations for training. Our results on challenging datasets compare favorably with state of the art results. The combination with the synthetic data allows our method yielding good results in profile alignment. That highlights the potential of using synthetic data for in-the-wild face alignment.

引用

页码：705 / 716

页数：12