Development and Optimization of a Novel Deep Learning Model for Diagnosis of Quince Leaf Diseases

Articles in Press

Document Type : Research Article

Authors

• A. Naderi Beni
• H. Bagherpour
• J. Amiri Parian

Department of Biosystems Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran

10.22067/jam.2024.88013.1248

Abstract

Introduction
Detection of tree leaf diseases plays a crucial role in the horticultural field. These diseases can originate from viruses, bacteria, fungi, and other pathogens. If proper attention is not given, these diseases can drastically affect trees, reducing both the quality and quantity of yields. Due to the importance of quince in Iran's export market, its diseases can cause significant economic losses to the country. Therefore, if leaf diseases can be automatically identified, appropriate actions can be taken in advance to mitigate these losses. Traditionally, the identification and detection of tree diseases rely on experts' naked-eye observations. However, the physical condition of the expert such as eyesight, fatigue, and work pressure can affect their decision-making capability. Today, deep convolutional neural networks (DCNNs), a novel approach to image classification, have become the most crucial detection method. DCNNs improve detection or classification accuracy by developing machine-learning models with many hidden layers to extract optimal features. This approach has significantly enhanced the classification and identification of diseases affecting plants and trees. This study employs a novel CNN algorithm alongside two pre-trained models to effectively identify and classify various types of quince diseases.
Materials and Methods
Images of healthy and diseased leaves were acquired from several databases. The majority of these images were sourced from the Agricultural Research Center of Isfahan Province in Iran, supplemented by contributions from researchers who had previously studied in this field. Other supporting datasets were obtained from internet sources. This study incorporated a total of 1,600 images, which included 390 images of fire blight, 384 images of leaf blight, 406 images of powdery mildew, and 420 images of healthy leaves. Of all the images obtained, 70%, 20%, and 10% were randomly selected for the network's training, validation, and testing, respectively. Image flipping, rotation, and zooming were applied to augment the training dataset. In this research, a proposed convolutional neural network (CNN) combined with image processing was developed to classify quince leaf diseases into four distinct classes. Three CNN models, including Inception-ResNet-v2, ResNet-101, and our proposed CNN model, were investigated, and their performances were compared using essential indices including precision, sensitivity, F1-score, and accuracy. To optimize the models’ performance, the impact of dropout with a 50% probability and the number of neurons in the hidden layers were examined. Our proposed CNN model consists of an architecture with four convolutional layers, with 224 × 224 RGB images as input to the first layer, which has 16 filters, followed by additional convolutional layers with 32, 64, and 128 filters respectively. Activation functions of ReLU combined with max-pooling were used at each convolutional layer, and Softmax activation was applied in the last layer of the neural network to convert the output into a probability distribution.
Results and Discussion
Three confusion matrices based on the test dataset were constructed for all the CNN models to compare and evaluate the performance of the classifiers. The indices obtained from the confusion matrices indicated that Inception-ResNet-v2 and ResNet-101 achieved accuracies of 79% and 72%, respectively. While all models exhibited promising efficiency in classifying leaf diseases, the proposed shallow CNN model stood out with an impressive accuracy of 91%, marking it as the most effective solution. The comprehensive results indicate that the optimized CNN model, featuring four convolutional layers, one hidden layer with 64 neurons, and a dropout rate of 0.5, outperformed the transfer learning models.
Conclusion
The findings of this study demonstrate that our developed proposed CNN model provides a high-performance solution for the rapid identification of quince leaf diseases. It excels in real-time detection and monitoring, achieving remarkable accuracy. Notably, it can identify fire blight and powdery mildew with a precision exceeding 95%.

Keywords

• Confusion matrix
• Convolutional neural network
• Fire blight
• Leaf blight
• Powdery mildew

Main Subjects

• Precision Farming

©2024 The author(s). This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0)

References

1. Ali, M. M., Bachik, N. A., Muhadi, N., Yusof, T. N. T., & Gomes, C. (2019). Non-destructive techniques of detecting plant diseases: A review. Physiological and Molecular Plant Pathology, 108, 101426. https://doi.org/10.1016/j.pmpp.2019.101426
2. Al-Zughbi, I., & Krayem, M. (2022). Quince fruit Cydonia oblonga Mill nutritional composition, antioxidative properties, health benefits and consumers preferences towards some industrial quince products: A review. Food Chemistry, 393, 133362. https://doi.org/10.1016/j.foodchem.2022.133362
3. Baldi, P., & Sadowski, P. (2014). The dropout learning algorithm. Artificial Intelligence, 210, 78-122.
4. Bradshaw, M., Braun, U., Götz, M., & Jurick, W. (2022). Phylogeny and taxonomy of powdery mildew caused by Erysiphe species on Lupinus hosts. Mycologia, 114(1), 76-88. https://doi.org/10.1080/00275514.2021.1973287
5. Chen, J., Liu, Q., & Gao, L. (2019). Visual tea leaf disease recognition using a convolutional neural network model. Symmetry, 11, 343. https://doi.org/10.3390/sym11030343.
6. Chen, R. C., Dewi, C., Huang, S. W., & Caraka, R. E. (2020). Selecting critical features for data classification based on machine learning methods. Journal of Big Data 7, 52. https://doi.org/10.1186/s40537-020-00327-4
7. Cruz, A., Ampatzidis, Y., Pierro, R., Materazzi, A., Panattoni, A., De Bellis, L., & Luvisi, A. (2019). Detection of grapevine yellows symptoms in Vitis vinifera with artificial intelligence. Computers and Electronics in Agriculture, 157, 63-76. https://doi.org/10.1016/j.compag.2018.12.028
8. Dai, G., & Fan, J. (2022). An industrial-grade solution for crop disease image detection tasks. Frontiers in Plant Science., 13, 921057. https://doi.org/10.3389/fpls.2022.921057.
9. David, M. (2023). Quince tree for the UK gardener. Retrieved March 28, 2024, from https://gardenfocused.co.uk/fruitarticles/quince.php
10. Dawod, R. G., & Dobre, C. (2022). Upper and lower leaf side detection with machine learning methods. Sensors, 22, 2696. https://doi.org/10.3390/s22072696
11. FAO. (2021). Crops production data. Retrieved from http://www.fao.org/faostat
12. Farokhzad,, Modaress Motlagh, A., Ahmadi Moghaddam, P., Jalali Honarmand, S., & Kheiralipour, K. (2024). A machine learning system to identify progress level of dry rot disease in potato tuber based on digital thermal image processing. Scientific Reports, 14(1), 1995. https://doi.org/10.1038/s41598-023-50948-x
13. Gupta, T. (2017). Plant leaf disease analysis using image-processing technique with modified SVM-CS classifier. International Journal of Engineering & Management Technology, 5, 11-17.
14. Gutiérrez, S., Hernández, I., Ceballos, S., Barrio, I., Díez-Navajas, A. M., & Tardaguila, J. (2021). Deep learning for the differentiation of downy mildew and spider mite in grapevine under field conditions. Computers and Electronics in Agriculture, 182,105991. https://doi.org/10.1016/j.compag.2021.105991
15. Harteveld, D. O. C., Akinsanmi, O. A., & Drenth, A. (2013). Multiple Alternaria species groups are associated with leaf blotch and fruit spot diseases of apple in Australia. Plant Pathology, 62(2), 289-297. https://doi.org/10.1111/j.1365-3059.2012.02637.x
16. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition(pp. 770-778).
17. Hosainpour, A., Kheiralipour, K., Nadimi, M., & Paliwal, J. (2022). Quality assessment of dried white mulberry (Morus alba) using machine vision. Horticulturae, 8(11), 1011. https://doi.org/10.3390/horticulturae8111011
18. Hossain, S., Mou, R. M., Hasan, M. M., Chakraborty, S., & Razzak, M. A. (2018). Recognition and detection of tea leaf’s diseases using support vector machine. In Proceedings of the 2018 IEEE 14^th International Colloquium on Signal Processing & Its Applications (CSPA), Penang, Malaysia. https://doi.org/1109/CSPA.2018.8368703
19. Islam, M., Dinh, A., Wahid, K., & Bhowmik, P. (2017). Detection of potato diseases using image segmentation and multiclass support vector machine. In Proceedings of the 30th IEEE Canadian Conference on Electrical andComputer Engineering, Windsor, ON, Canada, pp. 1-4. https://doi.org/1109/CCECE.2017.7946594
20. Jiang, F., Lu, Y., Chen, Y., Cai, D., & Li, G. (2020). Image recognition of four rice leaf diseases based on deep learning and support vector machine. Computers and Electronics in Agriculture, 179. https://doi.org/10.1016/j.compag.2020.105824.
21. Joshi, R. C., Kaushik, M., Dutta, M. K., Srivastava, A., & Choudhary, N. (2021). VirLeafNet: automatic analysis and viral disease diagnosis using deep-learning in Vigna mungo plant. Ecological Informatics. https://doi.org/10.1016/j.ecoinf.2020.101197
22. Kawasaki,, Uga, H., Kagiwada, S., & Iyatomi, H. (2015). Basic study of automated diagnosis of viral plant diseases using convolutional neural networks. In Proceedings of the 12th International Symposium on Visual Computing, Las Vegas, NV, USA, pp. 638-645. https://doi.org/10.1016/j.neucom.2017.06.023
23. Kheiralipour, K., Nadimi, M., & Paliwal, J. (2022). Development of an intelligent imaging system for ripeness determination of wild pistachios. Sensors, 22(19), 7134. https://doi.org/10.3390/s22197134
24. Lu, Y., Yi, S., Zeng, N., Liu, Y., & Zhang, Y. (2017). Identification of Rice diseases using deep convolutional neural networks, Neuro Computing, 267, 378-384. https://doi.org/10.1016/j.neucom.2017.06.023
25. Mianjy, P., Arora, R., &Vidal, R. (2018), July. On the implicit bias of dropout. In International conference on machine learning(pp. 3540-3548). PMLR.
26. Miranda, J. L., Gerardo, B. D., & Tanguilig, B. T. (2014). Pest detection and extraction using image processing techniques. International Journal of Computer and Communication Engineering, 3, 189. https://doi.org/7763/IJCCE.2014.V3.317
27. Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection, Frontiers in Plant Science, 7, 1419. https://doi.org/10.3389/fpls.2016.01419
28. Moore, J. (2022). Quince tree disease – Quince leaf blight. Retrieved April 1, 2024, from https://www.pyracantha.co.uk/quince-tree-disease-quince-leaf-blight.
29. Qin, F., Liu, D. X., Sun, B. D., Ruan, L., Ma, Z., & Wang, H. (2016). Identification of alfalfa leaf diseases using image recognition technology. PLoS ONE, 11. https://doi.org/10.1371/journalpone.0168274.
30. Rothe, P., & Kshirsagar, R. V. (2015). Cotton leaf disease identification using pattern recognition techniques. In Proceedings of the 2015 International Conference on Pervasive Computing, Pune, India, 1-6. https://doi.org/10.1109/PERVASIVE.2015.7086983
31. Saygili, H., Aysan, Y., Mirik, M., & Sahin, F. (2004), July. Severe outbreak of fire blight on quince in Turkey. In X International Workshop on Fire Blight, 704, 51-54. https://doi.org/10.17660/ActaHortic.2006.704.4
32. Shojaeian, A., Bagherpour, H., Bagherpour, R., Parian, J. A., Fatehi, F., & Taghinezhad, E. (2023). The Potential Application of Innovative Methods in Neural Networks for Surface Crack Recognition of Unshelled Hazelnut. Journal of Food Processing and Preservation, 2023. https://doi.org/10.1155/2023/2177724
33. Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D., & Stefanovic, D. (2016). Deep neural networks-based recognition of plant diseases by leaf image classification. Computational Intelligence and Neuroscience, https://doi.org/10.1155/2016/3289801
34. Sujatha, R., Chatterjee, J. M., Jhanjhi, N. Z., & Brohi, S. N. (2021). Performance of deep learning vs machine learning in plant leaf disease detection. Microprocess. Microsyst. https://doi.org/10.1016/j.micpro.2020.103615
35. Sun, C., Huang, C., Zhang, H., Chen, B., An, F., Wang, L., & Yun, T. (2022). Individual tree crown segmentation and crown width extraction from a heightmap derived from aerial laser scanning data using a deep learning framework. Frontiers in Plant Science, 13, 914-974. https://doi.org/10.3389/fpls.2022.914974
36. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition(pp. 2818-2826).
37. Taner, A., Öztekin, Y. B., & Duran, H. (2021). Performance analysis of deep learning CNN models for variety classification in hazelnut. Sustainability, 13(12), 6527. https://doi.org/10.3390 /su13126527
38. Tian, Y., Yang, G., Wang, Z., Wang, H., Li, E., & Liang, Z. (2019). Apple detection during different growth stages in orchards using the improved YOLO-V3 model. Computers and Electronics in Agriculture., 157, 417-426. https://doi.org/10.1016/j.compag.2019.01.012
39. Tiwari, V., Joshi, R. C., & Dutta, M. K. (2021). Dense convolutional neural networks based multiclass plant disease detection and classification using leaf images. Ecological Informatics, 63, 101289. https://doi.org/10.1016/j.ecoinf.2021.101289
40. Vidyarthi, S. K., Singh, S. K., Xiao, H. W., & Tiwari, R. (2021). Deep learnt grading of almond kernels. Journal of Food Process Engineering, 44(4), p.e13662.
41. Yang, L., Luo, J., Wang, Z., Chen, Y., & Wu, C. (2019). Research on recognition for cotton spider mites’ damage level based on deep learning. International Journal of Agricultural and Biological Engineering, 12(6), 129. https://doi.org/134. 10.25165/j.ijabe.20191206.4816