Pose-Robust Face Alignment with Adaptive Supervised Descent Method
Face alignment is a key component in facial processing. It is a challenging task because human facial images in real-world usually contain large variations due to the differences in pose, illumination, etc. Shape init-ialization and feature extraction are crucial in face landmark alignment. This pap...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2020-04-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/CN/abstract/abstract2168.shtml |
| _version_ | 1818355840666566656 |
|---|---|
| author | ZHAO Hui, JING Liping, YU Jian |
| author_facet | ZHAO Hui, JING Liping, YU Jian |
| author_sort | ZHAO Hui, JING Liping, YU Jian |
| collection | DOAJ |
| description | Face alignment is a key component in facial processing. It is a challenging task because human facial images in real-world usually contain large variations due to the differences in pose, illumination, etc. Shape init-ialization and feature extraction are crucial in face landmark alignment. This paper proposes a pose-robust face alignment model based on adaptive supervised descent method (SDM). Firstly, in order to reduce the influence of pose differences for face alignment, this paper uses clustering algorithm to cluster the face images into three categories (frontal faces, left faces, right faces) according to pose. Thus, the pose in each cluster is more compact. Secondly, face alignment can be taken as a coarse-to-fine supervised learning process with multi-stage. Therefore, the adaptive block size of feature extraction (from big to small) is used to get discriminative features. Based on the above two strategies, within each cluster, a better initial shape is given and the discriminant regression model is trained for facial landmark localization via adaptive SDM. A series of experiments have been conducted on benchmark datasets LFPW, HELEN and 300W. The experimental results show that this method makes facial landmark localization accurately in large pose images, and demonstrate the superiority of the proposed method by comparing with existing methods. |
| first_indexed | 2024-12-13T19:47:43Z |
| format | Article |
| id | doaj.art-b19f64cf441649bd90acc958100c5442 |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-12-13T19:47:43Z |
| publishDate | 2020-04-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-b19f64cf441649bd90acc958100c54422022-12-21T23:33:31ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182020-04-0114464965610.3778/j.issn.1673-9418.1905087Pose-Robust Face Alignment with Adaptive Supervised Descent MethodZHAO Hui, JING Liping, YU Jian01. College of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China 2. Beijing Key Lab of Traffic Data Analysis and Mining (Beijing Jiaotong University), Beijing 100044, ChinaFace alignment is a key component in facial processing. It is a challenging task because human facial images in real-world usually contain large variations due to the differences in pose, illumination, etc. Shape init-ialization and feature extraction are crucial in face landmark alignment. This paper proposes a pose-robust face alignment model based on adaptive supervised descent method (SDM). Firstly, in order to reduce the influence of pose differences for face alignment, this paper uses clustering algorithm to cluster the face images into three categories (frontal faces, left faces, right faces) according to pose. Thus, the pose in each cluster is more compact. Secondly, face alignment can be taken as a coarse-to-fine supervised learning process with multi-stage. Therefore, the adaptive block size of feature extraction (from big to small) is used to get discriminative features. Based on the above two strategies, within each cluster, a better initial shape is given and the discriminant regression model is trained for facial landmark localization via adaptive SDM. A series of experiments have been conducted on benchmark datasets LFPW, HELEN and 300W. The experimental results show that this method makes facial landmark localization accurately in large pose images, and demonstrate the superiority of the proposed method by comparing with existing methods.http://fcst.ceaj.org/CN/abstract/abstract2168.shtmlface alignmentfacial landmark localizationsupervised descent method (sdm) modelpose-robustadaptive feature block size |
| spellingShingle | ZHAO Hui, JING Liping, YU Jian Pose-Robust Face Alignment with Adaptive Supervised Descent Method Jisuanji kexue yu tansuo face alignment facial landmark localization supervised descent method (sdm) model pose-robust adaptive feature block size |
| title | Pose-Robust Face Alignment with Adaptive Supervised Descent Method |
| title_full | Pose-Robust Face Alignment with Adaptive Supervised Descent Method |
| title_fullStr | Pose-Robust Face Alignment with Adaptive Supervised Descent Method |
| title_full_unstemmed | Pose-Robust Face Alignment with Adaptive Supervised Descent Method |
| title_short | Pose-Robust Face Alignment with Adaptive Supervised Descent Method |
| title_sort | pose robust face alignment with adaptive supervised descent method |
| topic | face alignment facial landmark localization supervised descent method (sdm) model pose-robust adaptive feature block size |
| url | http://fcst.ceaj.org/CN/abstract/abstract2168.shtml |
| work_keys_str_mv | AT zhaohuijinglipingyujian poserobustfacealignmentwithadaptivesuperviseddescentmethod |