An Effective Approach for Potato Leaf Disease Classification Using Deep Learning

Öz

This study comparatively investigates the performance of deep learning and hybrid approaches for the detection and classification of potato leaf diseases (early blight, late blight, and healthy). In the first stage, direct image classification was performed using pre-trained deep learning models DenseNet201, ResNet50V2, VGG16, and Xception. Of these models, the VGG16 model achieved the highest accuracy. In the second stage, the same deep learning models were used as feature extractors, and the resulting features were classified using traditional machine learning algorithms, SVM, KNN, RF, and XGB. These hybrid approaches provided a significant increase in classification performance. The findings revealed that DenseNet201's combination of SVM and XGB exhibited superior performance with an overall accuracy rate of 99.31%. These results demonstrate that the powerful feature extraction capabilities of deep learning architectures, combined with the effective classification power of traditional machine learning algorithms, provide higher accuracy and reliability compared to the direct deep learning approach. The study highlights the potential of hybrid approaches, particularly for applications such as agricultural image processing and plant disease detection.

Anahtar Kelimeler

• potato leaf disease
• agriculture
• machine learning
• deep learning

Derin Öğrenme Kullanılarak Patates Yaprak Hastalığının Sınıflandırılması İçin Etkili Bir Yaklaşım

Öz

Bu çalışma, patates yaprak hastalıklarının (erken yanıklık, geç yanıklık ve sağlıklı) tespiti ve sınıflandırılmasında derin öğrenme ve hibrit yaklaşımların performansını karşılaştırmalı olarak incelemektedir. İlk aşamada, önceden eğitilmiş derin öğrenme modelleri DenseNet201, ResNet50V2, VGG16 ve Xception kullanılarak doğrudan görüntü sınıflandırması yapılmıştır. Bu modeller arasında VGG16 modeli en yüksek doğruluğu elde etmiştir. İkinci aşamada, aynı derin öğrenme modelleri özellik çıkarıcı olarak kullanılmış ve elde edilen özellikler geleneksel makine öğrenmesi algoritmaları olan SVM, KNN, RF ve XGB kullanılarak sınıflandırılmıştır. Bu hibrit yaklaşımlar sınıflandırma performansında önemli bir artış sağlamıştır. Bulgular, DenseNet201'in SVM ve XGB kombinasyonunun %99,31'lik genel bir doğruluk oranıyla üstün bir performans sergilediğini ortaya koymuştur. Bu sonuçlar, derin öğrenme mimarilerinin güçlü özellik çıkarma yeteneklerinin, geleneksel makine öğrenmesi algoritmalarının etkili sınıflandırma gücüyle birleştiğinde, doğrudan derin öğrenme yaklaşımına kıyasla daha yüksek doğruluk ve güvenilirlik sağladığını göstermektedir. Çalışma, özellikle tarımsal görüntü işleme ve bitki hastalığı tespiti gibi uygulamalar için hibrit yaklaşımların potansiyelini vurgulamaktadır.

Anahtar Kelimeler

• Patates yaprağı hastalığı
• tarım
• derin öğrenme
• makine öğrenimi

Kaynakça

1. [1] A. Dogra, S. Kadry, B. Goyal, and S. Agrawal, “An efficient image integration algorithm for night mode vision applications,” Multimedia Tools and Applications, vol. 79, no. 15–16, pp. 10995–11012, 2020. https://doi.org/10.1007/S11042-018-6631-Z/TABLES/3
2. [2] J. Tian, J. Chen, X. Ye, and S. Chen, “Health benefits of the potato affected by domestic cooking: A review,” Food Chemistry, vol. 202, pp. 165–175, 2016. https://doi.org/10.1016/J.FOODCHEM.2016.01.120
3. [3] C.M. Andre, S. Legay, C. Iammarino, et al., “The Potato in the Human Diet: a Complex Matrix with Potential Health Benefits,” Potato Research, vol. 57, no. 3, pp. 201–214, 2014. https://doi.org/10.1007/s11540-015-9287-3
4. [4] A. Singh and H. Kaur, “Potato Plant Leaves Disease Detection and Classification using Machine Learning Methodologies,” IOP Conference Series: Materials Science and Engineering, vol. 1022, no. 1, p. 012121, 2021. https://doi.org/10.1088/1757-899X/1022/1/012121
5. [5] E. Aksoy, U. Demirel, A. Bakhsh, et al., “Recent Advances in Potato (Solanum tuberosum L.) Breeding,” Advances in Plant Breeding Strategies: Vegetable Crops: Volume 8: Bulbs, Roots and Tubers, pp. 409–487, 2021. https://doi.org/10.1007/978-3-030-66965-2_10
6. [6] H.N. Fones, D.P. Bebber, T.M. Chaloner, W.T. Kay, G. Steinberg, and S.J. Gurr, “Threats to global food security from emerging fungal and oomycete crop pathogens,” Nature Food, vol. 1, no. 6, pp. 332–342, 2020. https://doi.org/10.1038/S43016-020-0075-0
7. [7] V. Lehsten, L. Wiik, A. Hannukkala, et al., “Earlier occurrence and increased explanatory power of climate for the first incidence of potato late blight caused by Phytophthora infestans in Fennoscandia,” PLOS ONE, vol. 12, no. 5, p. e0177580, 2017. https://doi.org/10.1371/JOURNAL.PONE.0177580
8. [8] S.S. Ray, N. Jain, R.K. Arora, S. Chavan, and S. Panigrahy, “Utility of Hyperspectral Data for Potato Late Blight Disease Detection,” Journal of the Indian Society of Remote Sensing, vol. 39, no. 2, pp. 161–169, 2011. https://doi.org/10.1007/S12524-011-0094-2/TABLES/6

9. [9] P. Nolte, J. Miller, K.M. Duellman, A.J. Gevens, and E. Banks, “Disease Management,” Potato Production Systems, pp. 203–257, 2020. https://doi.org/10.1007/978-3-030-39157-7_9
10. [10] A. Shukla and V. Ratan, “Management of Early Blight of Potato by Using Different Bioagents as Tuber Dressing and its Effect on Germination and Growth,” International Journal of Current Microbiology and Applied Sciences, vol. 8, no. 06, pp. 1965–1970, 2019. https://doi.org/10.20546/IJCMAS.2019.806.233
11. [11] I.K. Abuley and B.J. Nielsen, “Evaluation of models to control potato early blight (Alternaria solani) in Denmark,” Crop Protection, vol. 102, pp. 118–128, 2017. https://doi.org/10.1016/J.CROPRO.2017.08.012
12. [12] A. Abbas, U. Maqsood, S. Ur Rehman, K. Mahmood, T. Alsaedi, and M. Kundi, “An Artificial Intelligence Framework for Disease Detection in Potato Plants,” Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12628–12635, 2024. https://doi.org/10.48084/ETASR.6456
13. [13] R.A. Sholihati, I.A. Sulistijono, A. Risnumawan, and E. Kusumawati, “Potato Leaf Disease Classification Using Deep Learning Approach,” IES 2020 - International Electronics Symposium: The Role of Autonomous and Intelligent Systems for Human Life and Comfort, pp. 392–397, 2020. https://doi.org/10.1109/IES50839.2020.9231784
14. [14] S. Iftikhar, A.A. Shahid, S.A. Halim, et al., “Discovering novel Alternaria solani succinate dehydrogenase inhibitors by in silico modeling and virtual screening strategies to combat early blight,” Frontiers in Chemistry, vol. 5, no. NOV, p. 300609, 2017. https://doi.org/10.3389/FCHEM.2017.00100/BIBTEX
15. [15] P. Tm, A. Pranathi, K. Saiashritha, N.B. Chittaragi, and S.G. Koolagudi, “Tomato Leaf Disease Detection Using Convolutional Neural Networks,” 2018 11th International Conference on Contemporary Computing, IC3 2018, p. 2018. https://doi.org/10.1109/IC3.2018.8530532
16. [16] M. Yang, P. Kumar, J. Bhola, and M. Shabaz, “Development of image recognition software based on artificial intelligence algorithm for the efficient sorting of apple fruit,” International Journal of System Assurance Engineering and Management, vol. 13, no. 1, pp. 322–330, 2022. https://doi.org/10.1007/S13198-021-01415-1/TABLES/1
17. [17] K.P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018. https://doi.org/10.1016/J.COMPAG.2018.01.009
18. [18] K. Golhani, S.K. Balasundram, G. Vadamalai, and B. Pradhan, “A review of neural networks in plant disease detection using hyperspectral data,” Information Processing in Agriculture, vol. 5, no. 3, pp. 354–371, 2018. https://doi.org/10.1016/J.INPA.2018.05.002
19. [19] M. Aamir, M. Irfan, T. Ali, et al., “An Adoptive Threshold-Based MultiLevel Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification,” Diagnostics 2020, Vol. 10, Page 602, vol. 10, no. 8, p. 602, 2020. https://doi.org/10.3390/DIAGNOSTICS10080602
20. [20] M.A. Iqbal and K.H. Talukder, “Detection of Potato Disease Using Image Segmentation and Machine Learning,” 2020 International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2020, pp. 43–47, 2020. https://doi.org/10.1109/WISPNET48689.2020.9198563
21. [21] K.K. Chakraborty, R. Mukherjee, C. Chakroborty, and K. Bora, “Automated recognition of optical image based potato leaf blight diseases using deep learning,” Physiological and Molecular Plant Pathology, vol. 117, p. 101781, 2022. https://doi.org/10.1016/J.PMPP.2021.101781
22. [22] P. Jha, D. Dembla, and W. Dubey, “Deep learning models for enhancing potato leaf disease prediction: Implementation of transfer learning based stacking ensemble model,” Multimedia Tools and Applications, vol. 83, no. 13, pp. 37839–37858, 2024. https://doi.org/10.1007/S11042-023- 16993-4
23. [23] M. Ashikuzzaman, K. Roy, A. Lamon, and S. Abedin, “Potato Leaf Disease Detection By Deep Learning: A Comparative Study,” Proceedings - 6th International Conference on Electrical Engineering and Information and Communication Technology, ICEEICT 2024, pp. 278–283, 2024. https://doi.org/10.1109/ICEEICT62016.2024.10534467
24. [24] R. Mahum, H. Munir, Z.U.N. Mughal, et al., “A novel framework for potato leaf disease detection using an efficient deep learning model,” Human and Ecological Risk Assessment: An International Journal, vol. 29, no. 2, pp. 303–326, 2023. https://doi.org/10.1080/10807039.2022.2064814
25. [25] C.C. Bonik, F. Akter, M.H. Rashid, and A. Sattar, “A Convolutional Neural Network Based Potato Leaf Diseases Detection Using SequentialModel,” 2023 International Conference for Advancement in Technology, ICONAT 2023, p. 2023. https://doi.org/10.1109/ICONAT57137.2023.10080063
26. [26] J. Chen, X. Deng, Y. Wen, W. Chen, A. Zeb, and D. Zhang, “Weaklysupervised learning method for the recognition of potato leaf diseases,” Artificial Intelligence Review, vol. 56, no. 8, pp. 7985–8002, 2023. https://doi.org/10.1007/S10462-022-10374-3/FIGURES/6
27. [27] S.M. Alhammad, D.S. Khafaga, W.M. El-hady, F.M. Samy, and K.M. Hosny, “Deep learning and explainable AI for classification of potato leaf diseases,” Frontiers in Artificial Intelligence, vol. 7, p. 1449329, 2024. https://doi.org/10.3389/FRAI.2024.1449329/BIBTEX
28. [28] G. Huang, Z. Liu, L. Van Der Maaten, and K.Q. Weinberger, “Densely Connected Convolutional Networks,” Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700–4708, 2017. https://doi.org/10.1109/CVPR.2017.243
29. [29] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016. https://doi.org/10.1109/CVPR.2016.90
30. [30] F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” p. 2017. https://doi.org/10.1109/CVPR.2017.195
31. [31] K. Simonyan and A. Zisserman, “VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION,” Computer Vision and Pattern Recognition, p. 2015.
32. [32] Jayadeva, R. Khemchandani, and S. Chandra, “Twin support vector machines for pattern classification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 5, pp. 905–910, 2007. https://doi.org/10.1109/TPAMI.2007.1068
33. [33] M.A. Chandra and S.S. Bedi, “Survey on SVM and their application in image classification,” International Journal of Information Technology (Singapore), vol. 13, no. 5, pp. 1–11, 2021. https://doi.org/10.1007/S41870-017-0080-1/TABLES/1
34. [34] D. Lopez-Bernal, D. Balderas, P. Ponce, and A. Molina, “Education 4.0: Teaching the Basics of KNN, LDA and Simple Perceptron Algorithms for Binary Classification Problems,” Future Internet 2021, Vol. 13, Page 193, vol. 13, no. 8, p. 193, 2021. https://doi.org/10.3390/FI13080193
35. [35] J. Hu and S. Szymczak, “A review on longitudinal data analysis with random forest,” Briefings in Bioinformatics, vol. 24, no. 2, pp. 1–11, 2023. https://doi.org/10.1093/BIB/BBAD002
36. [36] A. Ibrahem Ahmed Osman, A. Najah Ahmed, M.F. Chow, Y. Feng Huang, and A. El-Shafie, “Extreme gradient boosting (Xgboost) model to predict the groundwater levels in Selangor Malaysia,” Ain Shams Engineering Journal, vol. 12, no. 2, pp. 1545–1556, 2021. https://doi.org/10.1016/J.ASEJ.2020.11.011
37. [37] “Plant Village Dataset,”
38. [38] Ş. Aykat and S. Senan, “Derin Öğrenme Kullanılarak Fundus Görüntülerinden Katarakt ve Diyabetik Retinopati Tespiti,” Mühendislik Bilimleri ve Araştırmaları Dergisi, vol. 5, no. 2, pp. 312–324, 2023. https://doi.org/10.46387/BJESR.1332567