Disease Detection and Identification of Rice Leaf Based on Improved Detection Transformer
In recent years, the domain of diagnosing plant afflictions has predominantly relied upon the utilization of deep learning techniques for classifying images of diseased specimens; however, these classification algorithms remain insufficient for instances where a single plant exhibits multiple ailmen...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/13/7/1361 |
| _version_ | 1797590702675197952 |
|---|---|
| author | Hua Yang Xingquan Deng Hao Shen Qingfeng Lei Shuxiang Zhang Neng Liu |
| author_facet | Hua Yang Xingquan Deng Hao Shen Qingfeng Lei Shuxiang Zhang Neng Liu |
| author_sort | Hua Yang |
| collection | DOAJ |
| description | In recent years, the domain of diagnosing plant afflictions has predominantly relied upon the utilization of deep learning techniques for classifying images of diseased specimens; however, these classification algorithms remain insufficient for instances where a single plant exhibits multiple ailments. Consequently, we view the region afflicted by the malady of rice leaves as a minuscule issue of target detection, and then avail ourselves of a computational approach to vision to identify the affected area. In this paper, we advance a proposal for a Dense Higher-Level Composition Feature Pyramid Network (DHLC-FPN) that is integrated into the Detection Transformer (DETR) algorithm, thereby proffering a novel Dense Higher-Level Composition Detection Transformer (DHLC-DETR) methodology which can effectively detect three diseases: sheath blight, rice blast, and flax spot. Initially, the proposed DHLC-FPN is utilized to supersede the backbone network of DETR through amalgamation with Res2Net, thus forming a feature extraction network. Res2Net then extracts five feature scales, which are coalesced through the deployment of high-density rank hybrid sampling by the DHLC-FPN architecture. The fused features, in concert with the location encoding, are then fed into the transformer to produce predictions of classes and prediction boxes. Lastly, the prediction classes and the prediction boxes are subjected to binary matching through the application of the Hungarian algorithm. On the IDADP datasets, the DHLC-DETR model, through the utilization of data enhancement, elevated mean Average Precision (mAP) by 17.3% in comparison to the DETR model. Additionally, mAP for small target detection was improved by 9.5%, and the magnitude of hyperparameters was reduced by 324.9 M. The empirical outcomes demonstrate that the optimized structure for feature extraction can significantly enhance the average detection accuracy and small target detection accuracy of the model, achieving an average accuracy of 97.44% on the IDADP rice disease dataset. |
| first_indexed | 2024-03-11T01:24:17Z |
| format | Article |
| id | doaj.art-2d93385818104e71ba137874ca493fcc |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-11T01:24:17Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-2d93385818104e71ba137874ca493fcc2023-11-18T17:52:44ZengMDPI AGAgriculture2077-04722023-07-01137136110.3390/agriculture13071361Disease Detection and Identification of Rice Leaf Based on Improved Detection TransformerHua Yang0Xingquan Deng1Hao Shen2Qingfeng Lei3Shuxiang Zhang4Neng Liu5School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430040, ChinaSchool of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430040, ChinaBaijuncheng Technology Co., Ltd., Wuhan 434000, ChinaSchool of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430040, ChinaSchool of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430040, ChinaSchool of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430040, ChinaIn recent years, the domain of diagnosing plant afflictions has predominantly relied upon the utilization of deep learning techniques for classifying images of diseased specimens; however, these classification algorithms remain insufficient for instances where a single plant exhibits multiple ailments. Consequently, we view the region afflicted by the malady of rice leaves as a minuscule issue of target detection, and then avail ourselves of a computational approach to vision to identify the affected area. In this paper, we advance a proposal for a Dense Higher-Level Composition Feature Pyramid Network (DHLC-FPN) that is integrated into the Detection Transformer (DETR) algorithm, thereby proffering a novel Dense Higher-Level Composition Detection Transformer (DHLC-DETR) methodology which can effectively detect three diseases: sheath blight, rice blast, and flax spot. Initially, the proposed DHLC-FPN is utilized to supersede the backbone network of DETR through amalgamation with Res2Net, thus forming a feature extraction network. Res2Net then extracts five feature scales, which are coalesced through the deployment of high-density rank hybrid sampling by the DHLC-FPN architecture. The fused features, in concert with the location encoding, are then fed into the transformer to produce predictions of classes and prediction boxes. Lastly, the prediction classes and the prediction boxes are subjected to binary matching through the application of the Hungarian algorithm. On the IDADP datasets, the DHLC-DETR model, through the utilization of data enhancement, elevated mean Average Precision (mAP) by 17.3% in comparison to the DETR model. Additionally, mAP for small target detection was improved by 9.5%, and the magnitude of hyperparameters was reduced by 324.9 M. The empirical outcomes demonstrate that the optimized structure for feature extraction can significantly enhance the average detection accuracy and small target detection accuracy of the model, achieving an average accuracy of 97.44% on the IDADP rice disease dataset.https://www.mdpi.com/2077-0472/13/7/1361rice leaf disease diagnosisobject detectionDETRdeep learningimage processing |
| spellingShingle | Hua Yang Xingquan Deng Hao Shen Qingfeng Lei Shuxiang Zhang Neng Liu Disease Detection and Identification of Rice Leaf Based on Improved Detection Transformer Agriculture rice leaf disease diagnosis object detection DETR deep learning image processing |
| title | Disease Detection and Identification of Rice Leaf Based on Improved Detection Transformer |
| title_full | Disease Detection and Identification of Rice Leaf Based on Improved Detection Transformer |
| title_fullStr | Disease Detection and Identification of Rice Leaf Based on Improved Detection Transformer |
| title_full_unstemmed | Disease Detection and Identification of Rice Leaf Based on Improved Detection Transformer |
| title_short | Disease Detection and Identification of Rice Leaf Based on Improved Detection Transformer |
| title_sort | disease detection and identification of rice leaf based on improved detection transformer |
| topic | rice leaf disease diagnosis object detection DETR deep learning image processing |
| url | https://www.mdpi.com/2077-0472/13/7/1361 |
| work_keys_str_mv | AT huayang diseasedetectionandidentificationofriceleafbasedonimproveddetectiontransformer AT xingquandeng diseasedetectionandidentificationofriceleafbasedonimproveddetectiontransformer AT haoshen diseasedetectionandidentificationofriceleafbasedonimproveddetectiontransformer AT qingfenglei diseasedetectionandidentificationofriceleafbasedonimproveddetectiontransformer AT shuxiangzhang diseasedetectionandidentificationofriceleafbasedonimproveddetectiontransformer AT nengliu diseasedetectionandidentificationofriceleafbasedonimproveddetectiontransformer |