3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network
Aiming at the low accuracy of large-pose face alignment, a cascade network based on truncated Alexnet is designed and implemented in the paper. The parallel convolution pooling layers are added for concatenating parallel results in the original deep convolution neural network, which improves the acc...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Advances in Condensed Matter Physics |
| Online Access: | http://dx.doi.org/10.1155/2020/6675014 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546878050271232 |
|---|---|
| author | Qian Zhang Hao Zheng Tao Yan Jiehui Li |
| author_facet | Qian Zhang Hao Zheng Tao Yan Jiehui Li |
| author_sort | Qian Zhang |
| collection | DOAJ |
| description | Aiming at the low accuracy of large-pose face alignment, a cascade network based on truncated Alexnet is designed and implemented in the paper. The parallel convolution pooling layers are added for concatenating parallel results in the original deep convolution neural network, which improves the accuracy of the output. Sending the intermediate parameter which is the result of each iteration into CNN and iterating repeatedly to optimize the pose parameter in order to get more accurate results of face alignment. To verify the effectiveness of this method, this paper tests on the AFLW and AFLW2000-3D datasets. Experiments on datasets show that the normalized average error of this method is 5.00% and 5.27%. Compared with 3DDFA, which is a current popular algorithm, the accuracy is improved by 0.60% and 0.15%, respectively. |
| format | Article |
| id | doaj-art-6165cf5ee7044e5296a05b760b463d92 |
| institution | Kabale University |
| issn | 1687-8108 1687-8124 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Condensed Matter Physics |
| spelling | doaj-art-6165cf5ee7044e5296a05b760b463d922025-02-03T06:46:47ZengWileyAdvances in Condensed Matter Physics1687-81081687-81242020-01-01202010.1155/2020/667501466750143D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade NetworkQian Zhang0Hao Zheng1Tao Yan2Jiehui Li3School of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaSchool of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaSchool of Information Engineering, Putian University, Putian, Fujian 351100, ChinaSchool of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaAiming at the low accuracy of large-pose face alignment, a cascade network based on truncated Alexnet is designed and implemented in the paper. The parallel convolution pooling layers are added for concatenating parallel results in the original deep convolution neural network, which improves the accuracy of the output. Sending the intermediate parameter which is the result of each iteration into CNN and iterating repeatedly to optimize the pose parameter in order to get more accurate results of face alignment. To verify the effectiveness of this method, this paper tests on the AFLW and AFLW2000-3D datasets. Experiments on datasets show that the normalized average error of this method is 5.00% and 5.27%. Compared with 3DDFA, which is a current popular algorithm, the accuracy is improved by 0.60% and 0.15%, respectively.http://dx.doi.org/10.1155/2020/6675014 |
| spellingShingle | Qian Zhang Hao Zheng Tao Yan Jiehui Li 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network Advances in Condensed Matter Physics |
| title | 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network |
| title_full | 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network |
| title_fullStr | 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network |
| title_full_unstemmed | 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network |
| title_short | 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network |
| title_sort | 3d large pose face alignment method based on the truncated alexnet cascade network |
| url | http://dx.doi.org/10.1155/2020/6675014 |
| work_keys_str_mv | AT qianzhang 3dlargeposefacealignmentmethodbasedonthetruncatedalexnetcascadenetwork AT haozheng 3dlargeposefacealignmentmethodbasedonthetruncatedalexnetcascadenetwork AT taoyan 3dlargeposefacealignmentmethodbasedonthetruncatedalexnetcascadenetwork AT jiehuili 3dlargeposefacealignmentmethodbasedonthetruncatedalexnetcascadenetwork |