Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition
Face image captured under uncontrolled illumination conditions is one of the most significant challenges for real-world human face recognition systems. To overcome this problem, we proposed a novel method called adaptive multiple-layer retinex-based color face enhancement (AMRF) to enhance the face...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9652521/ |
| _version_ | 1819171878215876608 |
|---|---|
| author | Duong Binh Giap Tuyen Ngoc Le Jing-Wein Wang Chia-Nan Wang |
| author_facet | Duong Binh Giap Tuyen Ngoc Le Jing-Wein Wang Chia-Nan Wang |
| author_sort | Duong Binh Giap |
| collection | DOAJ |
| description | Face image captured under uncontrolled illumination conditions is one of the most significant challenges for real-world human face recognition systems. To overcome this problem, we proposed a novel method called adaptive multiple-layer retinex-based color face enhancement (AMRF) to enhance the face images. Firstly, we use an associative filter to decompose a color face image into illumination and reflectance components at multiple layers. Then, the illumination components in each layer are adjusted automatically by multiplying with corresponded illumination compensation coefficients calculated through a referenced Gaussian template. The enhanced color face image is finally obtained by composing the compensated illumination components with the integrated reflectance component based on the Retinex theory. The experiment was performed on four popular color face datasets: LFW, IJB-C, CMU Multi-PIE, and CMU-PIE. Our proposed method makes face images more precise, natural, and smooth. The experiment results show that AMRF’s image quality assessment scores are significantly better than the original and other enhanced methods’ images. Furthermore, AMRF considerably improves the recognition accuracy of deep learning-based face recognition models, such as FaceNet, and ArcFace. Finally, our proposed method also saves computational time comparing the other techniques. |
| first_indexed | 2024-12-22T19:58:17Z |
| format | Article |
| id | doaj.art-81c12a3477974c3895ab50b524ecd125 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T19:58:17Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-81c12a3477974c3895ab50b524ecd1252022-12-21T18:14:22ZengIEEEIEEE Access2169-35362021-01-01916821616823510.1109/ACCESS.2021.31360939652521Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based RecognitionDuong Binh Giap0https://orcid.org/0000-0001-8211-106XTuyen Ngoc Le1https://orcid.org/0000-0002-5155-2150Jing-Wein Wang2https://orcid.org/0000-0001-8585-642XChia-Nan Wang3https://orcid.org/0000-0002-2374-3830Department of Electronics Engineering, National Kaohsiung University of Science and Technology, Kaohsiung, TaiwanDepartment of Electronic Engineering, Ming Chi University of Technology, New Taipei City, TaiwanInstitute of Photonics Engineering, National Kaohsiung University of Science and Technology, Kaohsiung, TaiwanDepartment of Industrial Engineering and Management, National Kaohsiung University of Science and Technology, Kaohsiung, TaiwanFace image captured under uncontrolled illumination conditions is one of the most significant challenges for real-world human face recognition systems. To overcome this problem, we proposed a novel method called adaptive multiple-layer retinex-based color face enhancement (AMRF) to enhance the face images. Firstly, we use an associative filter to decompose a color face image into illumination and reflectance components at multiple layers. Then, the illumination components in each layer are adjusted automatically by multiplying with corresponded illumination compensation coefficients calculated through a referenced Gaussian template. The enhanced color face image is finally obtained by composing the compensated illumination components with the integrated reflectance component based on the Retinex theory. The experiment was performed on four popular color face datasets: LFW, IJB-C, CMU Multi-PIE, and CMU-PIE. Our proposed method makes face images more precise, natural, and smooth. The experiment results show that AMRF’s image quality assessment scores are significantly better than the original and other enhanced methods’ images. Furthermore, AMRF considerably improves the recognition accuracy of deep learning-based face recognition models, such as FaceNet, and ArcFace. Finally, our proposed method also saves computational time comparing the other techniques.https://ieeexplore.ieee.org/document/9652521/Retinex modelcolor face image enhancementillumination compensationface recognition |
| spellingShingle | Duong Binh Giap Tuyen Ngoc Le Jing-Wein Wang Chia-Nan Wang Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition IEEE Access Retinex model color face image enhancement illumination compensation face recognition |
| title | Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition |
| title_full | Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition |
| title_fullStr | Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition |
| title_full_unstemmed | Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition |
| title_short | Adaptive Multiple Layer Retinex-Enabled Color Face Enhancement for Deep Learning-Based Recognition |
| title_sort | adaptive multiple layer retinex enabled color face enhancement for deep learning based recognition |
| topic | Retinex model color face image enhancement illumination compensation face recognition |
| url | https://ieeexplore.ieee.org/document/9652521/ |
| work_keys_str_mv | AT duongbinhgiap adaptivemultiplelayerretinexenabledcolorfaceenhancementfordeeplearningbasedrecognition AT tuyenngocle adaptivemultiplelayerretinexenabledcolorfaceenhancementfordeeplearningbasedrecognition AT jingweinwang adaptivemultiplelayerretinexenabledcolorfaceenhancementfordeeplearningbasedrecognition AT chiananwang adaptivemultiplelayerretinexenabledcolorfaceenhancementfordeeplearningbasedrecognition |