Image Classification of Pests with Residual Neural Network Based on Transfer Learning
Source abstract
Abstract
Agriculture is regarded as one of the key food sources for humans throughout history. In some countries, more than 90% of the population lives on agriculture. However, pests are regarded as one of the major causes of crop loss worldwide. Accurate and automated technology to classify pests can help pest detection with great significance for early preventive measures. This paper proposes the solution of a residual convolutional neural network for pest identification based on transfer learning. The IP102 agricultural pest image dataset was adopted as the experimental dataset to achieve data augmentation through random cropping, color transformation, CutMix and other operations. The processing technology can bring strong robustness to the affecting factors such as shooting angles, light and color changes. The experiment in this study compared the ResNeXt-50 (32 × 4d) model in terms of classification accuracy with different combinations of learning rate, transfer learning and data augmentation. In addition, the experiment compared the effects of data enhancement on the classification performance of different samples. The results show that the model classification effect based on transfer learning is generally superior to that based on new learning. Compared with new learning, transfer learning can greatly improve the model recognition ability and significantly reduce the training time to achieve the same classification accuracy. It is also very important to choose the appropriate data augmentation technology to improve classification accuracy. The accuracy rate of classification can reach 86.95% based on the combination of transfer learning + fine-tuning and CutMix. Compared to the original model, the accuracy of classification of some smaller samples was significantly improved. Compared with the relevant studies based on the same dataset, the method in this paper can achieve higher classification accuracy for more effective application in the field of pest classification.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Smart Systems and Machine Learning · Machine Learning and ELM
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China
Key Laboratory of Grain Information Processing and Control, Henan University of Technology, Zhengzhou 450001, China
References (36)
Show source-provided references
1. Transgenic Plants: An Emerging Approach to Pest Control10.1038/nbt0297-137 ↗
2. Automatic Plant Pest Detection & Recognition Using K-Means Clustering Algorithm & Correspondence Filters
3. Tea Insect Pests Classification Based on Artificial Neural Networks
4. Fast and Accurate Detection and Classification of Plant Diseases
5. Plant Species Classification Using Deep Convolutional Neural Network10.1016/j.biosystemseng.2016.08.024 ↗
6. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, Curran Associates, Inc.
7. Real-Time 3D Face Alignment Using an Encoder-Decoder Network with an Efficient Deconvolution Layer10.1109/LSP.2020.3032277 ↗
8. (2022, March 24). CVPR 2017 Open Access Repository. Available online: https://openaccess.thecvf.com/content_cvpr_2017/html/Huang_Densely_Connected_Convolutional_CVPR_2017_paper.html.
9. Coronavirus Disease 2019 (COVID-19): Survival Analysis Using Deep Learning and Cox Regression Model10.1007/s10044-021-00958-0 ↗
10. Salem, H., Attiya, G., and El-Fishawy, N. (2015, January 29–30). Gene Expression Profiles Based Human Cancer Diseases Classification. Proceedings of the 2015 11th International Computer Engineering Conference (ICENCO), Cairo, Egypt.10.1109/ICENCO.2015.7416345 ↗
11. (2022, March 24). Deep Learning|Nature. Available online: https://www.nature.com/articles/nature14539.
12. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Advances in Neural Information Processing Systems, Curran Associates, Inc.
13. Fully Convolutional Networks for Semantic Segmentation10.1109/TPAMI.2016.2572683 ↗
14. Fine-Tuning Deep Convolutional Networks for Plant Recognition
15. Zhang, H., He, G., Peng, J., Kuang, Z., and Fan, J. (2018, January 10–12). Deep Learning of Path-Based Tree Classifiers for Large-Scale Plant Species Identification. Proceedings of the 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), Miami, FL, USA.10.1109/MIPR.2018.00013 ↗
16. Wu, X., Zhan, C., Lai, Y.-K., Cheng, M.-M., and Yang, J. (2019, January 15–20). IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00899 ↗
17. Multi-Level Learning Features for Automatic Classification of Field Crop Pests10.1016/j.compag.2018.07.014 ↗
18. Crop Pest Classification with a Genetic Algorithm-Based Weighted Ensemble of Deep Convolutional Neural Networks10.1016/j.compag.2020.105809 ↗
19. Insect Pest Image Detection and Recognition Based on Bio-Inspired Methods10.1016/j.ecoinf.2020.101089 ↗
20. Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv.
21. Research on Insect Pest Image Detection and Recognition Based on Bio-Inspired Methods10.1016/j.biosystemseng.2018.02.008 ↗
22. Bollis, E., Pedrini, H., and Avila, S. (2020, January 14–19). Weakly Supervised Learning Guided by Activation Mapping Applied to a Novel Citrus Pest Benchmark. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW50498.2020.00043 ↗
23. Feature Reuse Residual Networks for Insect Pest Recognition10.1109/ACCESS.2019.2938194 ↗
24. Insect Classification and Detection in Field Crops Using Modern Machine Learning Techniques
25. Crop Pest Classification Based on Deep Convolutional Neural Network and Transfer Learning10.1016/j.compag.2019.104906 ↗
26. Ung, H.T., Ung, H.Q., and Nguyen, B.T. (2021). An Efficient Insect Pest Classification Using Multiple Convolutional Neural Network Based Models. arXiv.10.3233/FAIA220287 ↗
27. Khan, M.K., and Ullah, M.O. (2022, January 17–19). Deep Transfer Learning Inspired Automatic Insect Pest Recognition. Proceedings of the 3rd International Conference on Computational Sciences and Technologies; Mehran University of Engineering and Technology, Jamshoro, Pakistan.
28. High Performing Ensemble of Convolutional Neural Networks for Insect Pest Image Detection10.1016/j.ecoinf.2021.101515 ↗
29. Recognizing Pests in Field-Based Images by Combining Spatial and Channel Attention Mechanism10.1109/ACCESS.2021.3132486 ↗
30. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.10.1109/CVPR.2016.90 ↗
31. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017). Aggregated Residual Transformations for Deep Neural Networks. arXiv.10.1109/CVPR.2017.634 ↗
32. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the Inception Architecture for Computer Vision. arXiv.10.1109/CVPR.2016.308 ↗
33. Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.
34. El-Shafai, W., Almomani, I., and AlKhayer, A. (2021). Visualized Malware Multi-Classification Framework Using Fine-Tuned CNN-Based Transfer Learning Models. Appl. Sci., 11.10.3390/app11146446 ↗
35. Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (2019). CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features. arXiv.10.1109/ICCV.2019.00612 ↗
36. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization