Crop Leaf Disease Image Super-Resolution and Identification With Dual Attention and Topology Fusion Generative Adversarial Network
For agricultural disease image identification, obtained images are typically unclear, which can lead to poor identification results in real production environments. The quality of an image has a significant impact on the identification accuracy of pre-trained image classifiers. To address this probl...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9042295/ |
| _version_ | 1819158299633778688 |
|---|---|
| author | Qiang Dai Xi Cheng Yan Qiao Youhua Zhang |
| author_facet | Qiang Dai Xi Cheng Yan Qiao Youhua Zhang |
| author_sort | Qiang Dai |
| collection | DOAJ |
| description | For agricultural disease image identification, obtained images are typically unclear, which can lead to poor identification results in real production environments. The quality of an image has a significant impact on the identification accuracy of pre-trained image classifiers. To address this problem, we propose a generative adversarial network with dual-attention and topology-fusion mechanisms called DATFGAN. This network can effectively transform unclear images into clear and high-resolution images. Additionally, the weight sharing scheme in our proposed network can significantly reduce the number of parameters. Experimental results demonstrate that DATFGAN yields more visually pleasing results than state-of-the-art methods. Additionally, treated images are evaluated based on identification tasks. The results demonstrate that the proposed method significantly outperforms other methods and is sufficiently robust for practical use. |
| first_indexed | 2024-12-22T16:22:27Z |
| format | Article |
| id | doaj.art-5b66764dea3f43f0841e7d27bf0d013f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T16:22:27Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5b66764dea3f43f0841e7d27bf0d013f2022-12-21T18:20:13ZengIEEEIEEE Access2169-35362020-01-018557245573510.1109/ACCESS.2020.29820559042295Crop Leaf Disease Image Super-Resolution and Identification With Dual Attention and Topology Fusion Generative Adversarial NetworkQiang Dai0https://orcid.org/0000-0002-8942-834XXi Cheng1https://orcid.org/0000-0001-7479-7575Yan Qiao2https://orcid.org/0000-0002-4407-1762Youhua Zhang3https://orcid.org/0000-0003-1519-4509School of Information and Computer, Anhui Agricultural University, Hefei, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Information and Computer, Anhui Agricultural University, Hefei, ChinaSchool of Information and Computer, Anhui Agricultural University, Hefei, ChinaFor agricultural disease image identification, obtained images are typically unclear, which can lead to poor identification results in real production environments. The quality of an image has a significant impact on the identification accuracy of pre-trained image classifiers. To address this problem, we propose a generative adversarial network with dual-attention and topology-fusion mechanisms called DATFGAN. This network can effectively transform unclear images into clear and high-resolution images. Additionally, the weight sharing scheme in our proposed network can significantly reduce the number of parameters. Experimental results demonstrate that DATFGAN yields more visually pleasing results than state-of-the-art methods. Additionally, treated images are evaluated based on identification tasks. The results demonstrate that the proposed method significantly outperforms other methods and is sufficiently robust for practical use.https://ieeexplore.ieee.org/document/9042295/Crop leaf diseaseattentiongenerative adversarial networkssuper-resolutionidentification |
| spellingShingle | Qiang Dai Xi Cheng Yan Qiao Youhua Zhang Crop Leaf Disease Image Super-Resolution and Identification With Dual Attention and Topology Fusion Generative Adversarial Network IEEE Access Crop leaf disease attention generative adversarial networks super-resolution identification |
| title | Crop Leaf Disease Image Super-Resolution and Identification With Dual Attention and Topology Fusion Generative Adversarial Network |
| title_full | Crop Leaf Disease Image Super-Resolution and Identification With Dual Attention and Topology Fusion Generative Adversarial Network |
| title_fullStr | Crop Leaf Disease Image Super-Resolution and Identification With Dual Attention and Topology Fusion Generative Adversarial Network |
| title_full_unstemmed | Crop Leaf Disease Image Super-Resolution and Identification With Dual Attention and Topology Fusion Generative Adversarial Network |
| title_short | Crop Leaf Disease Image Super-Resolution and Identification With Dual Attention and Topology Fusion Generative Adversarial Network |
| title_sort | crop leaf disease image super resolution and identification with dual attention and topology fusion generative adversarial network |
| topic | Crop leaf disease attention generative adversarial networks super-resolution identification |
| url | https://ieeexplore.ieee.org/document/9042295/ |
| work_keys_str_mv | AT qiangdai cropleafdiseaseimagesuperresolutionandidentificationwithdualattentionandtopologyfusiongenerativeadversarialnetwork AT xicheng cropleafdiseaseimagesuperresolutionandidentificationwithdualattentionandtopologyfusiongenerativeadversarialnetwork AT yanqiao cropleafdiseaseimagesuperresolutionandidentificationwithdualattentionandtopologyfusiongenerativeadversarialnetwork AT youhuazhang cropleafdiseaseimagesuperresolutionandidentificationwithdualattentionandtopologyfusiongenerativeadversarialnetwork |