Rice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 model
To ensure higher quality, capacity, and production of rice, it is vital to diagnose rice leaf disease in its early stage in order to decrease the usage of pesticides in agriculture which in turn avoids environmental damage. Hence, this article presents a Multi-scale YOLO v5 detection network to dete...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Environmental Research Communications |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2515-7620/acdece |
| _version_ | 1797794094642102272 |
|---|---|
| author | V Senthil Kumar M Jaganathan A Viswanathan M Umamaheswari J Vignesh |
| author_facet | V Senthil Kumar M Jaganathan A Viswanathan M Umamaheswari J Vignesh |
| author_sort | V Senthil Kumar |
| collection | DOAJ |
| description | To ensure higher quality, capacity, and production of rice, it is vital to diagnose rice leaf disease in its early stage in order to decrease the usage of pesticides in agriculture which in turn avoids environmental damage. Hence, this article presents a Multi-scale YOLO v5 detection network to detect and classify the rice crop disease in its early stage. The experiment is initially started by pre-processing the rice leaf images obtained from the RLD dataset, after which data set labels are created, which are then divided into train and test sets. DenseNet-201 is used as the backbone network and depth-aware instance segmentation is used to segment the different regions of rice leaf. Moreover, the proposed Bidirectional Feature Attention Pyramid Network (Bi-FAPN) is used for extracting the features from the segmented image and also enhances the detection of diseases with different scales. Furthermore, the feature maps are identified in the detection head, where the anchor boxes are then applied to the output feature maps to produce the final output vectors by the YOLO v5 network. The subset of channels or filters is pruned from different layers of deep neural network models through the principled pruning approach without affecting the full framework performance. The experiments are conducted with RLD dataset with different existing networks to verify the generalization ability of the proposed model. The effectiveness of the network is evaluated based on various parameters in terms of average precision, accuracy, average recall, IoU, inference time, and F1 score, which are achieved at 82.8, 94.87, 75.81, 0.71, 0.017, and 92.45 respectively. |
| first_indexed | 2024-03-13T02:57:49Z |
| format | Article |
| id | doaj.art-aabbb23ca6b045a1a51fa7f2a9cf4dad |
| institution | Directory Open Access Journal |
| issn | 2515-7620 |
| language | English |
| last_indexed | 2024-03-13T02:57:49Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Environmental Research Communications |
| spelling | doaj.art-aabbb23ca6b045a1a51fa7f2a9cf4dad2023-06-28T01:32:48ZengIOP PublishingEnvironmental Research Communications2515-76202023-01-015606501410.1088/2515-7620/acdeceRice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 modelV Senthil Kumar0https://orcid.org/0000-0001-8472-7570M Jaganathan1A Viswanathan2M Umamaheswari3J Vignesh4Department of Computer science and Engineering, Faculty of Engineering & Technology, SRM Institute of Science & Technology , Tiruchirapalli, Tamil Nadu, IndiaDepartment of Computer Science and Engineering, Malla Reddy Institute of Technology and Science , Hyderabad, Telangana, IndiaSchool of CSE, Vellore Institute of Technology , Vellore, 632014, Tamil Nadu, IndiaSchool of CSE, Vellore Institute of Technology , Vellore, 632014, Tamil Nadu, IndiaDepartment of Information technology, Malla Reddy Institute of technology & science , Hyderabad, Telangana, IndiaTo ensure higher quality, capacity, and production of rice, it is vital to diagnose rice leaf disease in its early stage in order to decrease the usage of pesticides in agriculture which in turn avoids environmental damage. Hence, this article presents a Multi-scale YOLO v5 detection network to detect and classify the rice crop disease in its early stage. The experiment is initially started by pre-processing the rice leaf images obtained from the RLD dataset, after which data set labels are created, which are then divided into train and test sets. DenseNet-201 is used as the backbone network and depth-aware instance segmentation is used to segment the different regions of rice leaf. Moreover, the proposed Bidirectional Feature Attention Pyramid Network (Bi-FAPN) is used for extracting the features from the segmented image and also enhances the detection of diseases with different scales. Furthermore, the feature maps are identified in the detection head, where the anchor boxes are then applied to the output feature maps to produce the final output vectors by the YOLO v5 network. The subset of channels or filters is pruned from different layers of deep neural network models through the principled pruning approach without affecting the full framework performance. The experiments are conducted with RLD dataset with different existing networks to verify the generalization ability of the proposed model. The effectiveness of the network is evaluated based on various parameters in terms of average precision, accuracy, average recall, IoU, inference time, and F1 score, which are achieved at 82.8, 94.87, 75.81, 0.71, 0.017, and 92.45 respectively.https://doi.org/10.1088/2515-7620/acdecerice leaf disease detectionbidirectional feature attention pyramid networkDenseNet-201YOLO v5 networkinstance segmentationagricultural industry |
| spellingShingle | V Senthil Kumar M Jaganathan A Viswanathan M Umamaheswari J Vignesh Rice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 model Environmental Research Communications rice leaf disease detection bidirectional feature attention pyramid network DenseNet-201 YOLO v5 network instance segmentation agricultural industry |
| title | Rice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 model |
| title_full | Rice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 model |
| title_fullStr | Rice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 model |
| title_full_unstemmed | Rice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 model |
| title_short | Rice leaf disease detection based on bidirectional feature attention pyramid network with YOLO v5 model |
| title_sort | rice leaf disease detection based on bidirectional feature attention pyramid network with yolo v5 model |
| topic | rice leaf disease detection bidirectional feature attention pyramid network DenseNet-201 YOLO v5 network instance segmentation agricultural industry |
| url | https://doi.org/10.1088/2515-7620/acdece |
| work_keys_str_mv | AT vsenthilkumar riceleafdiseasedetectionbasedonbidirectionalfeatureattentionpyramidnetworkwithyolov5model AT mjaganathan riceleafdiseasedetectionbasedonbidirectionalfeatureattentionpyramidnetworkwithyolov5model AT aviswanathan riceleafdiseasedetectionbasedonbidirectionalfeatureattentionpyramidnetworkwithyolov5model AT mumamaheswari riceleafdiseasedetectionbasedonbidirectionalfeatureattentionpyramidnetworkwithyolov5model AT jvignesh riceleafdiseasedetectionbasedonbidirectionalfeatureattentionpyramidnetworkwithyolov5model |