Optimized CNN-Based Transfer Learning Approach with ReduceLROnPlateau for Early Potato Leaf Disease Classification

Andi Sunyoto; Yoga Pristyanto; Anggit Ferdita Nugraha

doi:10.29207/resti.v10i5.7533

Authors

Andi Sunyoto Universitas Amikom Yogyakarta
Yoga Pristyanto Universitas Amikom Yogyakarta
Anggit Ferdita Nugraha Universitas Amikom Yogyakarta

DOI:

https://doi.org/10.29207/resti.v10i5.7533

Keywords:

early blight, late blight, potato leaf disease, reducelonplateau, transfer learning

Abstract

Potato leaf disease classification is important for supporting early disease detection and improving crop management. This study proposes an optimized CNN-based transfer learning approach for classifying potato leaf images into three classes: Early Blight, Healthy, and Late Blight. Six pre-trained architectures—InceptionV3, Xception, DenseNet121, EfficientNetB0, ResNet50, and MobileNet were evaluated using ImageNet weights. Each model was modified with a custom classification head consisting of Global Average Pooling, a dense layer with 1,024 neurons, dropout, and a Softmax output layer. The models were evaluated using 5-fold stratified cross-validation. A frozen baseline configuration was first established, followed by fine-tuning configurations that varied learning rate, dropout rate, number of unfrozen layers, and the use of ReduceLROnPlateau. Data augmentation was applied only to the training subset in each fold. Performance was assessed using accuracy, AUC, validation loss, confusion matrix, ROC curves, training time, inference time, and GFLOPs. The results showed that optimized fine-tuning improved the average accuracy from 0.9876 to 0.9975 and reduced the average validation loss from 0.0316 to 0.0025. The Xception with the HP3 configuration achieved the best performance, with a mean accuracy of 0.999444 and an AUC of 0.999997. However, EfficientNetB0 achieved a high accuracy of 0.998333 with only 0.80 GFLOPs per image, making it more suitable for efficiency-oriented deployment. These findings demonstrate that fine-tuned transfer learning combined with adaptive learning rate scheduling is effective for potato leaf disease classification. Because the optimized configurations differ from the frozen baseline in the number of unfrozen layers, the dropout rate, the learning rate, and the use of ReduceLROnPlateau simultaneously, the reported gain reflects the combined effect of these components rather than the isolated contribution of ReduceLROnPlateau. The results were obtained on PlantVillage images acquired under controlled conditions and should therefore be regarded as an upper reference rather than an estimate of performance under field condition.

Downloads

Download data is not yet available.

References

[1] N. E. M. Khalifa, M. H. N. Taha, L. M. A. El-Maged, and A. E. Hassanien, “Artificial Intelligence in Potato Leaf Disease Classification: A Deep Learning Approach,” 2021, pp. 63–79. doi: 10.1007/978-3-030-59338-4_4.

[2] T.-Y. Lee, J.-Y. Yu, Y.-C. Chang, and J.-M. Yang, “Health Detection for Potato Leaf with Convolutional Neural Network,” in 2020 Indo – Taiwan 2nd International Conference on Computing, Analytics and Networks (Indo-Taiwan ICAN), IEEE, Feb. 2020, pp. 289–293. doi: 10.1109/Indo-TaiwanICAN48429.2020.9181312.

[3] R. Balodi, S. Bisht, A. Ghatak, and K. H. Rao, “Plant Disease Diagnosis: Technological Advancements and Challenges,” Indian Phytopathol., vol. 70, no. 3, Sep. 2017, doi: 10.24838/ip.2017.v70.i3.72487.

[4] U. Barman, D. Sahu, G. G. Barman, and J. Das, “Comparative Assessment of Deep Learning to Detect the Leaf Diseases of Potato based on Data Augmentation,” in 2020 International Conference on Computational Performance Evaluation (ComPE), IEEE, Jul. 2020, pp. 682–687. doi: 10.1109/ComPE49325.2020.9200015.

[5] N. R. Deepa and N. Nagarajan, “Kuan noise filter with Hough transformation based reweighted linear program boost classification for plant leaf disease detection,” J. Ambient Intell. Humaniz. Comput., vol. 14, no. 1, p. 409, 2023, doi: 10.1007/s12652-022-04156-6.

[6] M. Islam, Anh Dinh, K. Wahid, and P. Bhowmik, “Detection of potato diseases using image segmentation and multiclass support vector machine,” in 2017 IEEE 30th Canadian Conference on Electrical and Computer Engineering (CCECE), IEEE, Apr. 2017, pp. 1–4. doi: 10.1109/CCECE.2017.7946594.

[7] Md. A. Iqbal and K. H. Talukder, “Detection of Potato Disease Using Image Segmentation and Machine Learning,” in 2020 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET), IEEE, Aug. 2020, pp. 43–47. doi: 10.1109/WiSPNET48689.2020.9198563.

[8] U. P. Singh, S. S. Chouhan, S. Jain, and S. Jain, “Multilayer Convolution Neural Network for the Classification of Mango Leaves Infected by Anthracnose Disease,” IEEE Access, vol. 7, pp. 43721–43729, 2019, doi: 10.1109/ACCESS.2019.2907383.

[9] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Comput. Electron. Agric., vol. 145, Feb. 2018, doi: 10.1016/j.compag.2018.01.009.

[10] J. Chen, X. Deng, Y. Wen, W. Chen, A. Zeb, and D. Zhang, “Weakly-supervised learning method for the recognition of potato leaf diseases,” Artif. Intell. Rev., vol. 56, no. 8, pp. 7985–8002, Sep. 2023, doi: 10.1007/s10462-022-10374-3.

[11] M. Agarwal, A. Singh, S. Arjaria, A. Sinha, and S. Gupta, “ToLeD: Tomato Leaf Disease Detection using Convolution Neural Network,” Procedia Comput. Sci., vol. 167, pp. 293–301, 2020, doi: 10.1016/j.procs.2020.03.225.

[12] G. Sambasivam and G. D. Opiyo, “A predictive machine learning application in agriculture: Cassava disease detection and classification with imbalanced dataset using convolutional neural networks,” Egyptian Informatics Journal, vol. 22, no. 1, Mar. 2021, doi: 10.1016/j.eij.2020.02.007.

[13] A. Dengel, “Special Issue on Artificial Intelligence in Agriculture,” KI - Künstliche Intelligenz, vol. 27, no. 4, pp. 309–311, Nov. 2013, doi: 10.1007/s13218-013-0275-y.

[14] D. Bonino and G. Procaccianti, “Exploiting semantic technologies in smart environments and grids: Emerging roles and case studies,” Sci. Comput. Program., vol. 95, pp. 112–134, Dec. 2014, doi: 10.1016/j.scico.2014.02.018.

[15] David. P. Hughes and M. Salathe, “An open access repository of images on plant health to enable the development of mobile disease diagnostics,” Nov. 2015, Accessed: Oct. 28, 2021. [Online]. Available: https://arxiv.org/abs/1511.08060

[16] B. Wu, Z. Liu, Z. Yuan, G. Sun, and C. Wu, “Reducing Overfitting in Deep Convolutional Neural Networks Using Redundancy Regularizer,” 2017, pp. 49–55. doi: 10.1007/978-3-319-68612-7_6.

[17] A. Buslaev, V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. A. Kalinin, “Albumentations: Fast and Flexible Image Augmentations,” Information, vol. 11, no. 2, p. 125, Feb. 2020, doi: 10.3390/info11020125.

[18] K. Sanjeev, N. K. Gupta, W. J. Jeberson, and S. Paswan, “Early Prediction of Potato Leaf Diseases Using ANN Classifier,” Oriental journal of computer science and technology, vol. 13, no. 0203, pp. 129–134, Jan. 2021, doi: 10.13005/ojcst13.0203.11.

[19] S. Kumar, S. Paswan, and R. Kumari, “Early prediction of potato tuber diseases using ann classifier,” Progressive Agriculture, vol. 22, no. 2, pp. 162–165, 2022, doi: 10.5958/0976-4615.2021.00003.x.

[20] R. A. Sholihati, I. A. Sulistijono, A. Risnumawan, and E. Kusumawati, “Potato Leaf Disease Classification Using Deep Learning Approach,” in 2020 International Electronics Symposium (IES), IEEE, Sep. 2020, pp. 392–397. doi: 10.1109/IES50839.2020.9231784.

[21] D. Tiwari, M. Ashish, N. Gangwar, A. Sharma, S. Patel, and S. Bhardwaj, “Potato Leaf Diseases Detection Using Deep Learning,” in 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS), IEEE, May 2020, pp. 461–466. doi: 10.1109/ICICCS48265.2020.9121067.

[22] A. J. Rozaqi and A. Sunyoto, “Identification of Disease in Potato Leaves Using Convolutional Neural Network (CNN) Algorithm,” in 2020 3rd International Conference on Information and Communications Technology (ICOIACT), IEEE, Nov. 2020, pp. 72–76. doi: 10.1109/ICOIACT50329.2020.9332037.

[23] C. Hou et al., “Recognition of early blight and late blight diseases on potato leaves based on graph cut segmentation,” J. Agric. Food Res., vol. 5, p. 100154, Sep. 2021, doi: 10.1016/J.JAFR.2021.100154.

[24] J. Johnson et al., “Enhanced Field-Based Detection of Potato Blight in Complex Backgrounds Using Deep Learning,” Plant Phenomics, vol. 2021, pp. 1–13, May 2021, doi: 10.34133/2021/9835724.

[25] K. K. Chakraborty, R. Mukherjee, C. Chakroborty, and K. Bora, “Automated recognition of optical image based potato leaf blight diseases using deep learning,” Physiol. Mol. Plant Pathol., vol. 117, p. 101781, Jan. 2022, doi: 10.1016/J.PMPP.2021.101781.

[26] Md. K. R. Asif, Md. A. Rahman, and Most. H. Hena, “CNN based Disease Detection Approach on Potato Leaves,” in 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), IEEE, Dec. 2020, pp. 428–432. doi: 10.1109/ICISS49785.2020.9316021.

[27] D. Das, M. Singh, S. S. Mohanty, and S. Chakravarty, “Leaf Disease Detection using Support Vector Machine,” in 2020 International Conference on Communication and Signal Processing (ICCSP), IEEE, Jul. 2020, pp. 1036–1040. doi: 10.1109/ICCSP48568.2020.9182128.

[28] J. Johnson et al., “Enhanced Field-Based Detection of Potato Blight in Complex Backgrounds Using Deep Learning,” Plant Phenomics, vol. 2021, p. 9835724, 2021, doi: https://doi.org/10.34133/2021/9835724.