Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks
With the continuous development of deep learning, face detection methods have made the greatest progress. For real-time detection, cascade CNN based on the lightweight model is still the dominant structure that predicts face in a coarse-to-fine manner with strong generalization ability. Compared to...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9195457/ |
| _version_ | 1818579388819570688 |
|---|---|
| author | Xiaochao Li Zhenjie Yang Hongwei Wu |
| author_facet | Xiaochao Li Zhenjie Yang Hongwei Wu |
| author_sort | Xiaochao Li |
| collection | DOAJ |
| description | With the continuous development of deep learning, face detection methods have made the greatest progress. For real-time detection, cascade CNN based on the lightweight model is still the dominant structure that predicts face in a coarse-to-fine manner with strong generalization ability. Compared to other methods, it is not required for a fixed size of the input. However, MTCNN still has poor performance in detecting tiny targets. To improve model generalization ability, we propose a Receptive Field Enhanced Multi-Task Cascaded CNN. This network takes advantage of the Inception-V2 block and receptive field block to enhance the feature discriminability and robustness for small targets. The experimental results show that the performance of our network is improved by 1.08% on the AFW, 2.84% on the PASCAL FACE, 1.31% on the FDDB, and 2.3%, 2.1%, and 6.6% on the three sub-datasets of the WIDER FACE benchmark in comparison with MTCNN respectively. Furthermore, our structure uses 16% fewer parameters. |
| first_indexed | 2024-12-16T07:00:55Z |
| format | Article |
| id | doaj.art-d3ddd40860564825b2408bb26a12aa55 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T07:00:55Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d3ddd40860564825b2408bb26a12aa552022-12-21T22:40:10ZengIEEEIEEE Access2169-35362020-01-01817492217493010.1109/ACCESS.2020.30237829195457Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural NetworksXiaochao Li0https://orcid.org/0000-0001-7469-7064Zhenjie Yang1https://orcid.org/0000-0002-2414-5058Hongwei Wu2Department of Microelectronics and Integrated Circuit, Xiamen University, Xiamen, ChinaDepartment of Microelectronics and Integrated Circuit, Xiamen University, Xiamen, ChinaXiamen Network Information Security Joint Laboratory, Xiamen, ChinaWith the continuous development of deep learning, face detection methods have made the greatest progress. For real-time detection, cascade CNN based on the lightweight model is still the dominant structure that predicts face in a coarse-to-fine manner with strong generalization ability. Compared to other methods, it is not required for a fixed size of the input. However, MTCNN still has poor performance in detecting tiny targets. To improve model generalization ability, we propose a Receptive Field Enhanced Multi-Task Cascaded CNN. This network takes advantage of the Inception-V2 block and receptive field block to enhance the feature discriminability and robustness for small targets. The experimental results show that the performance of our network is improved by 1.08% on the AFW, 2.84% on the PASCAL FACE, 1.31% on the FDDB, and 2.3%, 2.1%, and 6.6% on the three sub-datasets of the WIDER FACE benchmark in comparison with MTCNN respectively. Furthermore, our structure uses 16% fewer parameters.https://ieeexplore.ieee.org/document/9195457/Face detectioncascade convolutional neural networksreceptive field |
| spellingShingle | Xiaochao Li Zhenjie Yang Hongwei Wu Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks IEEE Access Face detection cascade convolutional neural networks receptive field |
| title | Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks |
| title_full | Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks |
| title_fullStr | Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks |
| title_full_unstemmed | Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks |
| title_short | Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks |
| title_sort | face detection based on receptive field enhanced multi task cascaded convolutional neural networks |
| topic | Face detection cascade convolutional neural networks receptive field |
| url | https://ieeexplore.ieee.org/document/9195457/ |
| work_keys_str_mv | AT xiaochaoli facedetectionbasedonreceptivefieldenhancedmultitaskcascadedconvolutionalneuralnetworks AT zhenjieyang facedetectionbasedonreceptivefieldenhancedmultitaskcascadedconvolutionalneuralnetworks AT hongweiwu facedetectionbasedonreceptivefieldenhancedmultitaskcascadedconvolutionalneuralnetworks |