Optimization of Convolutional Neural Networks Using Resizing Techniques for Banana Leaf Disease Classification

Aldiyansyah Kurniawan; Ade Irma Purnamasari; Denni Pratama; Edi Tohidi; Edi Wahyudin

doi:10.59934/jaiea.v5i2.1876

Authors

Aldiyansyah Kurniawan STMIK IKMI Cirebon
Ade Irma Purnamasari STMIK IKMI Cirebon
Denni Pratama STMIK IKMI Cirebon
Edi Tohidi STMIK IKMI Cirebon
Edi Wahyudin STMIK IKMI Cirebon

DOI:

https://doi.org/10.59934/jaiea.v5i2.1876

Keywords:

MobileNetV2, image resizing, banana leaf disease, deep learning, transfer learning

Abstract

Early and accurate identification of banana leaf diseases is essential for supporting digital agriculture, as visual symptoms often require rapid and reliable analysis. This study investigates the impact of three image resizing techniques squashing, letterboxing, and random resized crop on the performance of the MobileNetV2 architecture in classifying four categories of banana leaf images using the Banana Leaf Disease Dataset v4 consisting of 4,675 samples. The experiments were conducted using a transfer learning approach with an 80:10:10 data split, standardized normalization, and data augmentation. The results show that all resizing techniques achieved test accuracies above 92%. Squashing produced the highest accuracy and fastest training time, letterboxing demonstrated the most stable performance with the lowest validation loss, and random resized crop improved generalization to variations in object position. These findings confirm that resizing strategies significantly influence the stability and effectiveness of CNN models. Overall, MobileNetV2 proves capable of delivering accurate and efficient classification of banana leaf diseases when supported by an appropriate preprocessing pipeline. This study provides empirical evidence for developing image-based plant disease diagnosis systems within smart agriculture.

Downloads

Download data is not yet available.

References

M. Bagga and et al., “Image based detection and classification of plant diseases: A review,” [Journal name], 2024, doi: 10.1002/uar2.20053.

P. Sajitha, A. Andrushia, N. Mostafa, S. Y. Shdefat, and N. Anand, “A review of machine learning and deep learning image-based plant disease classification for industrial farming systems,” Sustain. Oper. Comput., 2024, doi: 10.1016/j.susoc.2023.03.001.

A. T. Khan and et al., “Plant disease detection model for edge computing devices,” Front. Plant Sci., vol. 14, 2023, doi: 10.3389/fpls.2023.1308528.

R. Archana and S. Jeevaraj, “Deep learning models for digital image processing: a review,” Artif. Intell. Rev., 2024, doi: 10.1007/s10462-023-10631-z.

J. Lu, L. Tan, and H. Jiang, “Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification,” Agriculture, vol. 11, no. 8, p. 707, 2021, doi: 10.3390/agriculture11080707.

A. Joshi, D. Guevara, and M. Earles, “Standardizing and centralizing datasets for efficient training of agricultural deep learning models,” Appl. Sci., vol. 15, no. 16, p. 9206, 2023, doi: 10.3390/app15169206.

S. Saponara and A. Elhanashi, “Impact of image resizing on deep learning detectors,” in Advances in Sensors and Sensing Technology, Springer, 2022, pp. 15–32. doi: 10.1007/978-3-030-95498-7_2.

O. Rukundo, “Effects of image size on deep learning,” Electronics, vol. 12, no. 4, p. 985, 2023, doi: 10.3390/electronics12040985.

H. Talebi and P. Milanfar, “Learning to resize images for vision tasks,” Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2021. doi: 10.48550/arXiv.2103.09950.

H. J. D. Koresh, A. H. Al-Kubati, and R. Kumar, “Impact of the preprocessing steps in deep learning based image classifications,” NAS Lett., vol. 47, no. 6, pp. 645–647, 2024, doi: 10.1007/s40009-023-01372-2.

Y. P. Liang, X. Wu, and Z. Chen, “Implementation of lightweight convolutional neural network for embedded systems: Impact of image resizing interpolation methods,” Sensors, vol. 24, no. 7, p. 2265, 2024, doi: 10.3390/s24072265.

A. R. Auni and E. Sugiharti, “Optimization of Mango Plant Leaf Disease Classification Using Concatenation Method of MobileNetV2 and DenseNet201 CNN Architectures,” Sci. J. Informatics, vol. 11, no. 4, pp. 1023–1034, 2025, doi: 10.15294/sji.v11i4.15169.

N. Helmawati and E. Utami, “Analysis for Detecting Banana Leaf Disease Using the CNN Method,” JUITA J. Inform., vol. 13, no. 1, pp. 29–36, 2025, doi: 10.30595/juita.v13i1.24514.

R. Arboretti, T. T. Aye, and D. Tondini, “Combining design of experiments and machine learning for process modeling: A systematic approach,” Comput. Ind. Eng., vol. 160, p. 107590, 2021, doi: 10.1016/j.cie.2021.107590.

N. Al Kharusi and E. López, “Design of experiments and machine learning integration in tissue engineering: A systematic review,” Heliyon, vol. 8, no. 11, p. e11624, 2022, doi: 10.1016/j.heliyon.2022.e11624.

H. Xu, J. Zhao, and L. Zhang, “Benchmarking AutoML frameworks for image classification: An experimental evaluation,” Neural Comput. Appl., vol. 36, no. 9, pp. 5317–5332, 2024, doi: 10.1007/s00521-023-08793-6.

V. Schiano di Cola et al., “Exploratory data analysis and supervised learning in plant phenotyping studies,” Commun. Appl. Ind. Math., vol. 15, no. 2, pp. 69–90, 2024, doi: 10.2478/caim-2024-0014.

N. Jiménez, J. López, P. García, and A. Martín, “Detection of leaf diseases in banana crops using deep learning techniques,” AI, vol. 6, no. 3, p. 61, 2025, doi: 10.3390/ai6030061.

K. Maharana, S. Mondal, and B. Nemade, “A review: Data pre processing and data augmentation techniques,” Glob. Transitions Proc., vol. 3, no. 1, pp. 91–99, 2022, doi: 10.1016/j.gltp.2022.04.020.

Y. Gulzar, F. Ahmad, A. Shafique, and S. Malik, “Fruit image classification model based on MobileNetV2 with deep transfer learning technique,” Sustainability, vol. 15, no. 3, p. 1906, 2023, doi: 10.3390/su15031906.

A. Batool, J. Kim, S.-J. Lee, J.-H. Yang, and Y.-C. Byun, “An Enhanced Lightweight T-Net Architecture Based on CNN for Tomato Plant Leaf Disease Classification,” PeerJ Comput. Sci., vol. 10, p. e2495, 2024, doi: 10.7717/peerj-cs.2495.