A salient feature establishment tactic for cassava disease recognition
Accurate classification of cassava disease, particularly in field scenarios, relies on object semantic localization to identify and precisely locate specific objects within an image based on their semantic meaning, thereby enabling targeted classification while suppressing irrelevant noise and focus...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2024-12-01
|
| Series: | Artificial Intelligence in Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589721724000436 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846123312777789440 |
|---|---|
| author | Jiayu Zhang Baohua Zhang Zixuan Chen Innocent Nyalala Kunjie Chen Junfeng Gao |
| author_facet | Jiayu Zhang Baohua Zhang Zixuan Chen Innocent Nyalala Kunjie Chen Junfeng Gao |
| author_sort | Jiayu Zhang |
| collection | DOAJ |
| description | Accurate classification of cassava disease, particularly in field scenarios, relies on object semantic localization to identify and precisely locate specific objects within an image based on their semantic meaning, thereby enabling targeted classification while suppressing irrelevant noise and focusing on key semantic features. The advancement of deep convolutional neural networks (CNNs) paved the way for identifying cassava diseases by leveraging salient semantic features and promising high returns. This study proposes an approach that incorporates three innovative elements to refine feature representation for cassava disease classification. First, a mutualattention method is introduced to highlight semantic features and suppress irrelevant background features in the feature maps. Second, instance batch normalization (IBN) was employed after the residual unit to construct salient semantic features using the mutualattention method, representing high-quality semantic features in the foreground. Finally, the RSigELUD activation method replaced the conventional ReLU activation, enhancing the nonlinear mapping capacity of the proposed neural network and further improving fine-grained leaf disease classification performance. This approach significantly aided in distinguishing subtle disease manifestations in cassava leaves. The proposed neural network, MAIRNet-101 (Mutualattention IBN RSigELUD Neural Network), achieved an accuracy of 95.30 % and an F1-score of 0.9531, outperforming EfficientNet-B5 and RepVGG-B3g4. To evaluate the generalization capability of MAIRNet, the FGVC-Aircraft dataset was used to train MAIRNet-50, which achieved an accuracy of 83.64 %. These results suggest that the proposed algorithm is well suited for cassava leaf disease classification applications and offers a robust solution for advancing agricultural technology. |
| format | Article |
| id | doaj-art-0ed1349e424d4e5da493060a43c29540 |
| institution | Kabale University |
| issn | 2589-7217 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Artificial Intelligence in Agriculture |
| spelling | doaj-art-0ed1349e424d4e5da493060a43c295402024-12-14T06:31:55ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172024-12-0114115132A salient feature establishment tactic for cassava disease recognitionJiayu Zhang0Baohua Zhang1Zixuan Chen2Innocent Nyalala3Kunjie Chen4Junfeng Gao5College of Engineering, Nanjing Agricultural University, Nanjing, 210000, Jiangsu Province, ChinaCollege of Engineering, Nanjing Agricultural University, Nanjing, 210000, Jiangsu Province, ChinaNanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing, Jiangsu 210014, ChinaCollege of Engineering, Nanjing Agricultural University, Nanjing, 210000, Jiangsu Province, China; Faculty of Science, Department of Computer Science, Egerton University, Njoro, KenyaCollege of Engineering, Nanjing Agricultural University, Nanjing, 210000, Jiangsu Province, China; Corresponding authors.Department of Computer Science, University of Aberdeen, UK; Corresponding authors.Accurate classification of cassava disease, particularly in field scenarios, relies on object semantic localization to identify and precisely locate specific objects within an image based on their semantic meaning, thereby enabling targeted classification while suppressing irrelevant noise and focusing on key semantic features. The advancement of deep convolutional neural networks (CNNs) paved the way for identifying cassava diseases by leveraging salient semantic features and promising high returns. This study proposes an approach that incorporates three innovative elements to refine feature representation for cassava disease classification. First, a mutualattention method is introduced to highlight semantic features and suppress irrelevant background features in the feature maps. Second, instance batch normalization (IBN) was employed after the residual unit to construct salient semantic features using the mutualattention method, representing high-quality semantic features in the foreground. Finally, the RSigELUD activation method replaced the conventional ReLU activation, enhancing the nonlinear mapping capacity of the proposed neural network and further improving fine-grained leaf disease classification performance. This approach significantly aided in distinguishing subtle disease manifestations in cassava leaves. The proposed neural network, MAIRNet-101 (Mutualattention IBN RSigELUD Neural Network), achieved an accuracy of 95.30 % and an F1-score of 0.9531, outperforming EfficientNet-B5 and RepVGG-B3g4. To evaluate the generalization capability of MAIRNet, the FGVC-Aircraft dataset was used to train MAIRNet-50, which achieved an accuracy of 83.64 %. These results suggest that the proposed algorithm is well suited for cassava leaf disease classification applications and offers a robust solution for advancing agricultural technology.http://www.sciencedirect.com/science/article/pii/S2589721724000436Cassava disease classificationIrrelevant feature depressionSemantic foreground representationSalient semantic featuresNegative eigenvalue maintain |
| spellingShingle | Jiayu Zhang Baohua Zhang Zixuan Chen Innocent Nyalala Kunjie Chen Junfeng Gao A salient feature establishment tactic for cassava disease recognition Artificial Intelligence in Agriculture Cassava disease classification Irrelevant feature depression Semantic foreground representation Salient semantic features Negative eigenvalue maintain |
| title | A salient feature establishment tactic for cassava disease recognition |
| title_full | A salient feature establishment tactic for cassava disease recognition |
| title_fullStr | A salient feature establishment tactic for cassava disease recognition |
| title_full_unstemmed | A salient feature establishment tactic for cassava disease recognition |
| title_short | A salient feature establishment tactic for cassava disease recognition |
| title_sort | salient feature establishment tactic for cassava disease recognition |
| topic | Cassava disease classification Irrelevant feature depression Semantic foreground representation Salient semantic features Negative eigenvalue maintain |
| url | http://www.sciencedirect.com/science/article/pii/S2589721724000436 |
| work_keys_str_mv | AT jiayuzhang asalientfeatureestablishmenttacticforcassavadiseaserecognition AT baohuazhang asalientfeatureestablishmenttacticforcassavadiseaserecognition AT zixuanchen asalientfeatureestablishmenttacticforcassavadiseaserecognition AT innocentnyalala asalientfeatureestablishmenttacticforcassavadiseaserecognition AT kunjiechen asalientfeatureestablishmenttacticforcassavadiseaserecognition AT junfenggao asalientfeatureestablishmenttacticforcassavadiseaserecognition AT jiayuzhang salientfeatureestablishmenttacticforcassavadiseaserecognition AT baohuazhang salientfeatureestablishmenttacticforcassavadiseaserecognition AT zixuanchen salientfeatureestablishmenttacticforcassavadiseaserecognition AT innocentnyalala salientfeatureestablishmenttacticforcassavadiseaserecognition AT kunjiechen salientfeatureestablishmenttacticforcassavadiseaserecognition AT junfenggao salientfeatureestablishmenttacticforcassavadiseaserecognition |