Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks
Most existing image quality assessment (IQA) methods focus on improving the performance of synthetic distorted images. Although these methods perform well on the synthetic distorted IQA database, once they are applied to the natural distorted database, the performance will severely decrease. In this...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8918423/ |
| _version_ | 1818645000423997440 |
|---|---|
| author | Hongtao Yang Ping Shi Dixiu Zhong Da Pan Zefeng Ying |
| author_facet | Hongtao Yang Ping Shi Dixiu Zhong Da Pan Zefeng Ying |
| author_sort | Hongtao Yang |
| collection | DOAJ |
| description | Most existing image quality assessment (IQA) methods focus on improving the performance of synthetic distorted images. Although these methods perform well on the synthetic distorted IQA database, once they are applied to the natural distorted database, the performance will severely decrease. In this work, we propose a blind image quality assessment based on generative adversarial network (BIQA-GAN) with its advantages of self-generating samples and self-feedback training to improve network performance. Three different BIQA-GAN models are designed according to the target domain of the generator. Comprehensive experiments on popular benchmarks show that our proposed method significantly outperforms the previous state-of-the-art methods for authentically distorted images, which also has good performances on synthetic distorted benchmarks. |
| first_indexed | 2024-12-17T00:23:47Z |
| format | Article |
| id | doaj.art-5c6b2e9a253a47b6ba560dcb7c263715 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T00:23:47Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5c6b2e9a253a47b6ba560dcb7c2637152022-12-21T22:10:30ZengIEEEIEEE Access2169-35362019-01-01717929017930310.1109/ACCESS.2019.29572358918423Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial NetworksHongtao Yang0https://orcid.org/0000-0003-3931-1239Ping Shi1Dixiu Zhong2Da Pan3Zefeng Ying4School of Information and Communication Engineering, Communication University of China, Beijing, ChinaSchool of Information and Communication Engineering, Communication University of China, Beijing, ChinaSchool of Information and Communication Engineering, Communication University of China, Beijing, ChinaSchool of Information and Communication Engineering, Communication University of China, Beijing, ChinaSchool of Information and Communication Engineering, Communication University of China, Beijing, ChinaMost existing image quality assessment (IQA) methods focus on improving the performance of synthetic distorted images. Although these methods perform well on the synthetic distorted IQA database, once they are applied to the natural distorted database, the performance will severely decrease. In this work, we propose a blind image quality assessment based on generative adversarial network (BIQA-GAN) with its advantages of self-generating samples and self-feedback training to improve network performance. Three different BIQA-GAN models are designed according to the target domain of the generator. Comprehensive experiments on popular benchmarks show that our proposed method significantly outperforms the previous state-of-the-art methods for authentically distorted images, which also has good performances on synthetic distorted benchmarks.https://ieeexplore.ieee.org/document/8918423/Generative adversarial networksdeep learningimage quality assessmentno-reference/blind image quality assessmentnatural distorted image |
| spellingShingle | Hongtao Yang Ping Shi Dixiu Zhong Da Pan Zefeng Ying Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks IEEE Access Generative adversarial networks deep learning image quality assessment no-reference/blind image quality assessment natural distorted image |
| title | Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks |
| title_full | Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks |
| title_fullStr | Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks |
| title_full_unstemmed | Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks |
| title_short | Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks |
| title_sort | blind image quality assessment of natural distorted image based on generative adversarial networks |
| topic | Generative adversarial networks deep learning image quality assessment no-reference/blind image quality assessment natural distorted image |
| url | https://ieeexplore.ieee.org/document/8918423/ |
| work_keys_str_mv | AT hongtaoyang blindimagequalityassessmentofnaturaldistortedimagebasedongenerativeadversarialnetworks AT pingshi blindimagequalityassessmentofnaturaldistortedimagebasedongenerativeadversarialnetworks AT dixiuzhong blindimagequalityassessmentofnaturaldistortedimagebasedongenerativeadversarialnetworks AT dapan blindimagequalityassessmentofnaturaldistortedimagebasedongenerativeadversarialnetworks AT zefengying blindimagequalityassessmentofnaturaldistortedimagebasedongenerativeadversarialnetworks |