Share Email Print
cover

Proceedings Paper • new

Deformable hourglass network with face region normalization for robust face alignment
Author(s): Rui Cheng; Huabin Wang; Xin Liu; Xiang Yan; Liang Tao
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Stacked hourglass (HG) networks have been successfully applied to face alignment. However, due to the complex geometry of the facial appearance, the HG model still lacks the robustness of aligning faces in large poses. In this paper, a two-step method is proposed for robust face alignment. First, by using a convolutional neural network (CNN) to directly output the transformation parameters, the conventional procedure of normalizing the face region by performing Procrustes analysis based on the detected landmarks and the mean shape is simplified. In this way, faces with different poses can be converted to a canonical state, which is more advantageous for subsequent face alignment. Second, motivated by recent deformable convolutional networks, we propose a modulated deformable residual block and replace the plain counterparts in the HG model, resulting in deformable hourglass networks (DHNs). The DHN yields large performance improvements over original HG model while having the almost same amount of parameters and bringing minor additional computation costs. Depending on the synergistic effect of two innovations, the proposed method achieves better performance in comparison to the state-of-the-art methods on challenging benchmark datasets.

Paper Details

Date Published: 3 January 2020
PDF: 10 pages
Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 1137303 (3 January 2020); doi: 10.1117/12.2557185
Show Author Affiliations
Rui Cheng, Anhui Univ. (China)
Huabin Wang, Anhui Univ. (China)
Xin Liu, Anhui Univ. (China)
Xiang Yan, Anhui Univ. (China)
Liang Tao, Anhui Univ. (China)


Published in SPIE Proceedings Vol. 11373:
Eleventh International Conference on Graphics and Image Processing (ICGIP 2019)
Zhigeng Pan; Xun Wang, Editor(s)

© SPIE. Terms of Use
Back to Top