Diagnosis of Paddy Diseases Using Pre-Trained Architectures and a Proposed Enhanced EfficientNetB3 Model

Abstract

Rice is an important crop in India and is often affected by pests and diseases, which can lead to a significant drop in production. This research investigates advanced deep learning approaches for accurate paddy disease diagnosis, focusing on comparing several transfer learning models. The study specifically targets diseases such as Tungro, Dead Heart, Hispa, Blast, Downy Mildew, Brown Spot, Bacterial Leaf Blight, Bacterial Panicle Blight, and Bacterial Leaf Streak. The base EfficientNetB3 model attains approximately 95.55 % accuracy during training and 95.12% during evaluation on unseen data. However, it encounters challenges when applied to domain-specific tasks such as diagnosing paddy diseases, frequently experiencing issues such as overfitting and inadequate convergence. To overcome these issues, an Enhanced EfficientNetB3 model was developed, incorporating batch normalization, dropout, and data regularization techniques. The training was conducted using the 'Paddy Doctor' dataset, featuring 10,407 high- resolution images of paddy leaves. It reached an accuracy of 98.92 % during training with a loss rate of 0.1385. For validation, the model reached an accuracy of 98.20 % and a loss rate of 0.1450. On an independent test set, the accuracy 98.50 % obtained with a test loss of 0.1505. With remarkable accuracy and a training time of just 68 minutes, the model demonstrates its significant potential for precise paddy disease diagnosis. Its impressive performance plays a crucial role in advancing disease management and boosting crop yields.

Keywords

• Paddy Disease Detection
• Transfer Learning
• Enhanced EfficientNetB3
• Deep Learning in Agriculture
• Precision Agriculture
• Image Classification

References

1. Bhujel S & Shakya S (2022). Rice leaf diseases classification using discriminative fine tuning and CLR on EfficientNet. Journal of Soft Computing Paradigm 4(3): 172-187. doi.org/10.30534/jscp/2022/05162022
2. Deb M, Dhal K G, Mondal R & Gálvez J (2021). Paddy disease classification study: A deep convolutional neural network approach. Optical Memory and Neural Networks 30: 338-357. doi.org/10.1134/S1063775821030077
3. Deng R, Tao M, Xing H, Yang X, Liu C, Liao K & Qi L (2021). Automatic diagnosis of rice diseases using deep learning. Frontiers in Plant Science 12: 701038. doi.org/10.3389/fpls.2021.701038
4. Dogra R, Rani S, Singh A, Albahar M A, Barrera A E & Alkhayyat A (2023). Deep learning model for detection of brown spot rice leaf disease with smart agriculture. Computers and Electrical Engineering 109: 108659. doi.org/10.1016/j.compeleceng.2023.108659
5. Dubey R K & Choubey D K (2024). Reliable detection of blast disease in rice plant using optimized artificial neural network. Agronomy Journal 116(3): 1099-1111
6. Ganesan G & Chinnappan J (2022). Hybridization of ResNet with YOLO classifier for automated paddy leaf disease recognition: An optimized model. Journal of Field Robotics 39(7): 1085-1109. doi.org/10.1002/rob.22085
7. Ganesan S, Sinha N & Sundararajan V (2023). A new hybrid deep learning model for classifying rice plant diseases. Journal of Computational Biology and Bioinformatics 17(2): 99-110. doi.org/10.1016/j.jcb.2023.103122
8. Gerdan D, Koç C & Vatandaş M (2023). Diagnosis of tomato plant diseases using pre-trained architectures and a proposed convolutional neural network model. Journal of Agricultural Sciences 29(2): 618-629

9. Hukkeri G S, Soundarya B C, Gururaj H L & Ravi V (2024). Classification of Various Plant Leaf Disease Using Pretrained Convolutional Neural Network on Imagenet. The Open Agriculture Journal 18(1). doi.org/10.2174/1874331502414010113
10. Kaur G & Sivia J S (2024). Development of deep and machine learning convolutional networks of variable spatial resolution for automatic detection of leaf blast disease of rice. Computers and Electronics in Agriculture 225: 109210. doi.org/10.1016/j.compag.2023.109210
11. Kiratiratanapruk K, Temniranrat P, Sinthupinyo W, Prempree P, Chaitavon K, Porntheeraphat S & Prasertsak A (2020). Development of paddy rice seed classification process using machine learning techniques for automatic grading machine. Journal of Sensors 2020(1): 7041310. doi.org/10.1155/2020/7041310
12. Kumar Y, Singh R, Moudgil M R & Kamini (2023). A systematic review of different categories of plant disease detection using deep learning-based approaches. Archives of Computational Methods in Engineering 30(8): 4757-4779. doi.org/10.1007/s11831-022-09783-x
13. Latif G, Abdelhamid S E, Mallouhy R E, Alghazo J & Kazimi Z A (2022). Deep learning utilization in agriculture: Detection of rice plant diseases using an improved CNN model. Plants 11(17): 2230. doi.org/10.3390/plants11172230
14. Li B, Liu B, Li S & Liu H (2022). An improved EfficientNet for rice germ integrity classification and recognition. Agriculture 12(6): 863. doi.org/10.3390/agriculture12060863
15. Liang K, Wang Y, Sun L, Xin D & Chang Z (2022). A lightweight-improved CNN based on VGG16 for identification and classification of rice diseases and pests. In The international conference on image, vision and intelligent systems (ICIVIS 2021) (pp. 195-207). Singapore: Springer Nature Singapore. doi.org/10.1007/978-981-16-7487- 8_19
16. Liu W, Yu L & Luo J (2022). A hybrid attention-enhanced DenseNet neural network model based on improved U-Net for rice leaf disease identification. Frontiers in Plant Science 13: 922809. doi.org/10.3389/fpls.2022.922809
17. Malvade N N, Yakkundimath R, Saunshi G B & Elemmi M C (2023). Paddy variety identification from field crop images using deep learning techniques. International Journal of Computational Vision and Robotics 13(4): 405-419. doi.org/10.1504/IJCVR.2023.129934
18. Meena R, Joshi S & Raghuwanshi S (2024). Xception model for disease detection in rice plant. Journal of Intelligent & Fuzzy Systems (Preprint): 1-18. doi.org/10.3233/JIFS-230473
19. Ozdemir C, Dogan Y & Kaya Y (2024). RGB-Angle-Wheel: A new data augmentation method for deep learning models. Knowledge-Based Systems, 291: 111615
20. Ozdemir C (2024). Adapting transfer learning models to dataset through pruning and Avg-TopK pooling. Neural Computing and Applications 36(11): 6257-6270
21. Ozdemir C, Dogan Y & Kaya Y (2024). A new local pooling approach for convolutional neural network: local binary pattern. Multimedia Tools and Applications 83(12): 34137-34151
22. Razavi M, Mavaddati S & Koohi H (2024). ResNet deep models and transfer learning technique for classification and quality detection of rice cultivars. Expert Systems with Applications 247: 123276. doi.org/10.1016/j.eswa.2023.123276
23. Rahman C R, Arko P S, Ali M E, Khan M A I, Apon S H, Nowrin F & Wasif A (2020). Identification and recognition of rice diseases and pests using convolutional neural networks. Biosystems Engineering 194: 112-120. doi.org/10.1016/j.biosystemseng.2020.03.003
24. Shah S R, Qadri S, Bibi H, Shah S M W, Sharif M I & Marinello F (2023). Comparing Inception V3, VGG 16, VGG 19, CNN, and ResNet 50: A case study on early detection of a rice disease. Agronomy 13(6): 1633. doi.org/10.3390/agronomy13061633
25. Simhadri C G, Kondaveeti H K, Vatsavayi V K, Mitra A & Ananthachari P (2024). Deep learning for rice leaf disease detection: A systematic literature review on emerging trends, methodologies and techniques. Information Processing in Agriculture.
26. Sun J, Zhang Y, Zhu X & Zhang Y D (2023). Enhanced individual characteristics normalized lightweight rice-VGG16 method for rice seed defect recognition. Multimedia Tools and Applications 82(3): 3953-3972. doi.org/10.1007/s11042-022-12954-2
27. Verma S, Kumar P & Singh J P (2024). A unified lightweight CNN-based model for disease detection and identification in corn, rice, and wheat. IETE Journal of Research 70(3): 2481-2492
28. Yakkundimath R, Saunshi G, Anami B & Palaiah S (2022). Classification of rice diseases using convolutional neural network models. Journal of The Institution of Engineers (India): Series B 103(4): 1047-1059. doi.org/10.1007/s40031-022-00732-0