3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network
Joint Authors
Zhang, Qian
Zheng, Hao
Yan, Tao
Li, Jiehui
Source
Advances in Condensed Matter Physics
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-8, 8 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-12-07
Country of Publication
Egypt
No. of Pages
8
Main Subjects
Abstract EN
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.
American Psychological Association (APA)
Zhang, Qian& Zheng, Hao& Yan, Tao& Li, Jiehui. 2020. 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network. Advances in Condensed Matter Physics،Vol. 2020, no. 2020, pp.1-8.
https://search.emarefa.net/detail/BIM-1126102
Modern Language Association (MLA)
Zhang, Qian…[et al.]. 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network. Advances in Condensed Matter Physics No. 2020 (2020), pp.1-8.
https://search.emarefa.net/detail/BIM-1126102
American Medical Association (AMA)
Zhang, Qian& Zheng, Hao& Yan, Tao& Li, Jiehui. 3D Large-Pose Face Alignment Method Based on the Truncated Alexnet Cascade Network. Advances in Condensed Matter Physics. 2020. Vol. 2020, no. 2020, pp.1-8.
https://search.emarefa.net/detail/BIM-1126102
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1126102