Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network
Aiming at the problem of a large number of parameters and high time complexity caused by the current deep convolutional neural network models, an improved face alignment algorithm of a cascaded convolutional neural network (CCNN) is proposed from the network structure, random perturbation factor (sh...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Advances in Multimedia |
| Online Access: | http://dx.doi.org/10.1155/2021/6654561 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832566354652168192 |
|---|---|
| author | Xun Duan Yuanshun Wang Yun Wu |
| author_facet | Xun Duan Yuanshun Wang Yun Wu |
| author_sort | Xun Duan |
| collection | DOAJ |
| description | Aiming at the problem of a large number of parameters and high time complexity caused by the current deep convolutional neural network models, an improved face alignment algorithm of a cascaded convolutional neural network (CCNN) is proposed from the network structure, random perturbation factor (shake), and data scale. The algorithm steps are as follows: 3 groups of lightweight CNNs are designed; the first group takes facial images with face frame as input, trains 3 CNNs in parallel, and weighted outputs the facial images with 5 facial key points (anchor points). Then, the anchor points and 2 different windows with a shake mechanism are used to crop out 10 partial images of human faces. The networks in the second group train 10 CNNs in parallel and every 2 networks’ weighted average and colocated a key point. Based on the second group of networks, the third group designed a smaller shake mechanism and windows, to achieve more fine-tuning. When training the network, the idea of parallel within groups and serial between groups is adopted. Experiments show that, on the LFPW face dataset, the improved CCNN in this paper is superior to any other algorithm of the same type in positioning speed, algorithm parameter amount, and test error. |
| format | Article |
| id | doaj-art-9bd720cd3a5f443d9daaad0021a3e959 |
| institution | Kabale University |
| issn | 1687-5680 1687-5699 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Multimedia |
| spelling | doaj-art-9bd720cd3a5f443d9daaad0021a3e9592025-02-03T01:04:25ZengWileyAdvances in Multimedia1687-56801687-56992021-01-01202110.1155/2021/66545616654561Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural NetworkXun Duan0Yuanshun Wang1Yun Wu2School of Computer Science and Technology, GuiZhou University, GuiYang 550025, ChinaSchool of Computer Science and Technology, GuiZhou University, GuiYang 550025, ChinaSchool of Computer Science and Technology, GuiZhou University, GuiYang 550025, ChinaAiming at the problem of a large number of parameters and high time complexity caused by the current deep convolutional neural network models, an improved face alignment algorithm of a cascaded convolutional neural network (CCNN) is proposed from the network structure, random perturbation factor (shake), and data scale. The algorithm steps are as follows: 3 groups of lightweight CNNs are designed; the first group takes facial images with face frame as input, trains 3 CNNs in parallel, and weighted outputs the facial images with 5 facial key points (anchor points). Then, the anchor points and 2 different windows with a shake mechanism are used to crop out 10 partial images of human faces. The networks in the second group train 10 CNNs in parallel and every 2 networks’ weighted average and colocated a key point. Based on the second group of networks, the third group designed a smaller shake mechanism and windows, to achieve more fine-tuning. When training the network, the idea of parallel within groups and serial between groups is adopted. Experiments show that, on the LFPW face dataset, the improved CCNN in this paper is superior to any other algorithm of the same type in positioning speed, algorithm parameter amount, and test error.http://dx.doi.org/10.1155/2021/6654561 |
| spellingShingle | Xun Duan Yuanshun Wang Yun Wu Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network Advances in Multimedia |
| title | Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network |
| title_full | Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network |
| title_fullStr | Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network |
| title_full_unstemmed | Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network |
| title_short | Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network |
| title_sort | face alignment algorithm based on an improved cascaded convolutional neural network |
| url | http://dx.doi.org/10.1155/2021/6654561 |
| work_keys_str_mv | AT xunduan facealignmentalgorithmbasedonanimprovedcascadedconvolutionalneuralnetwork AT yuanshunwang facealignmentalgorithmbasedonanimprovedcascadedconvolutionalneuralnetwork AT yunwu facealignmentalgorithmbasedonanimprovedcascadedconvolutionalneuralnetwork |