Comparative Analysis of Durian Leaf Disease Classification Using Transfer Learning VGG16, InceptionV3, and U-Net

Nafisa Maysa Salma; Rudi Kurniawan; Bani Nurhakim; Agus Bahtiar; Riri Narasati

doi:10.59934/jaiea.v5i2.1864

Authors

Nafisa Maysa Salma STMIK IKMI CIREBON
Rudi Kurniawan
Bani Nurhakim
Agus Bahtiar
Riri Narasati

DOI:

https://doi.org/10.59934/jaiea.v5i2.1864

Keywords:

durian leaf classification, transfer learning, VGG16, InceptionV3, U-Net

Abstract

Image-based durian leaf disease detection presents challenges due to high visual similarity among symptoms and the limited, imbalanced dataset. This study compares three deep learning architectures VGG16, InceptionV3, and U-Net encoder-based—using transfer learning for classifying five durian leaf conditions. The dataset of 4,437 images underwent preprocessing, augmentation, and preliminary segmentation using U-Net to enhance focus on leaf regions. Fine-tuning was applied to the upper layers of each model to adapt feature representations to tropical leaf characteristics. The results indicate that InceptionV3 achieved the most stable and accurate performance with an accuracy of approximately 0.66, while VGG16 showed balanced results but was more prone to overfitting. U-Net proved effective for segmentation but less optimal as a classifier due to loss of small-scale lesion details. Overall, the findings demonstrate that combining U-Net segmentation with CNN-based transfer learning improves disease identification performance, particularly under limited data conditions.

Downloads

Download data is not yet available.

References

W. B. Demilie, “Plant disease detection and classification techniques: A comparative study of the performances,” J. Big Data, vol. 11, p. 5, 2024, [Online]. Available: https://doi.org/10.1186/s40537-023-00863-9

T. Nyawose, R. C. Maswanganyi, and P. Khumalo, “A review on the detection of plant disease using machine learning and deep learning approaches ,” J. Imaging , vol. 11, no. 10. p. 326, 2025.

V. S. Dhaka, N. Kundu, G. Rani, E. Zumpano, and E. Vocaturo, “Role of Internet of Things and Deep Learning Techniques in Plant Disease Detection and Classification: A Focused Review ,” Sensors , vol. 23, no. 18. p. 7877, 2023.

S. M. Hassan, M. Jasinski, Z. Leonowicz, E. Jasinska, and A. K. Maji, “Plant Disease Identification Using Shallow Convolutional Neural Network ,” Agronomy , vol. 11, no. 12. p. 2388, 2021.

Z. Al Sahili and M. Awad, “The power of transfer learning in agricultural applications: AgriNet,” Int. J. Comput. Intell. Syst., vol. 15 AR–6, 2022, doi: 10.1007/s44196-022-00129-x.

M. Hossen, F. Rahman, and M. Uddin, “Transfer learning in agricultural image classification: Comparative evaluation of modern CNNs,” J. Smart Farming, vol. 5, no. 1, pp. 41–53, 2025.

M. Jangid and R. Sharma, “A review of convolutional neural networks in agriculture: VGG16 and InceptionV3 architectures in focus ,” Plant Leaf Disease Detection Journal , vol. 12, no. 4. pp. 345–362, 2023.

S. Pandey, K. Yogi, and A. Ranjan, “Hybrid (VGG16, ResNet50, InceptionV3 and MobileNet) model for wheat leaf diseases detection ,” JISEM , vol. 10, no. 36s. 2025.

A. Abu, M. Rahman, and S. Latip, “Transfer learning strategies for plant disease classification using deep CNN architectures,” J. Comput. Agric., vol. 14, no. 2, pp. 112–125, 2022.

K. I. Alexopoulos, R. Sapkota, M. Karkee, N. D. Tselikas, and D. K. Nasiopoulos, “Deep learning and computer vision in plant disease detection: A comprehensive review ,” Artificial Intelligence Review , vol. 58. p. 92, 2025.

T. N. Thanh, “A durian leaf image dataset of common diseases in agricultural environments,” Inf. Process. Agric., 2025, doi: 10.1016/j.inpa.2025.01.004.

M. O. Ojo and A. Zahid, “Improving deep learning classifiers performance via preprocessing and class imbalance approaches in a plant disease detection pipeline,” Agronomy, vol. 13, no. 3, p. 887, 2023, doi: 10.3390/agronomy13030887.

C. Xu, C. Yu, and S. Zhang, “Lightweight Multi-Scale Dilated U-Net for Crop Disease Leaf Image Segmentation,” Electronics, vol. 11, no. 23, p. 3947, 2022, doi: 10.3390/electronics11233947.

H. Wang et al., “MFBP-UNet: A network for pear leaf disease segmentation in natural agricultural environments,” Plants, vol. 12, no. 18, p. Article 3209, 2023, doi: 10.3390/plants12183209.

H. N. Ngugi, A. A. Akinyelu, and A. E. Ezugwu, “Machine learning and deep learning for crop disease diagnosis: performance analysis and review,” Agronomy, vol. 14, no. 12, p. 3001, 2024, doi: 10.3390/agronomy14123001.

W. Nawae et al., “Resequencing of durian genomes reveals large genetic variations among different cultivars,” Front. Plant Sci., vol. 14 AR–1, 2023, doi: 10.3389/fpls.2023.1137077.

A. Ghosh and J. Roberts, “Exploratory data analysis in image datasets for robust deep learning,” J. Mach. Vis. Appl., vol. 35, no. 4, pp. 2023–2040, 2024, doi: 10.1007/s00138-024-01456-7.

L. Li, S. Zhang, and B. Wang, “Plant disease detection and classification by deep learning—A review,” IEEE Access, vol. 9, pp. 56683–56698, 2021, doi: 10.1109/ACCESS.2021.3069646.

G. Sumalatha and J. R. Singothu, “Effectiveness of Data Augmentation Techniques in Plant Disease Detection Using Pretrained CNN Models,” NeuroQuantology, vol. 20, no. 15, 2022.

T. Kim, D. Shin, and D. Shin, “Data augmentation method for plant leaf disease recognition,” Appl. Sci., vol. 13, no. 3, p. 1465, 2023, doi: 10.3390/app13031465.

A. Chaudhary and R. B. Pachori, “Multiscale fully convolutional network for COVID-19 lesion segmentation from CT images,” Biomed. Signal Process. Control, vol. 66, p. 102495, 2021, doi: 10.1016/j.bspc.2021.102495.

G. Singh, S. Sharma, and P. Kaur, “Enhanced leaf disease segmentation using U-Net and adaptive feature refinement,” Plants, vol. 14, no. 3, p. 512, 2025, doi: 10.3390/plants14030512.

J. Cao, M. Yan, Y. Jia, X. Tian, and Z. Zhang, “Application of a modified Inception-v3 model in the dynasty-based classification of ancient murals,” EURASIP J. Adv. Signal Process., p. 49, 2021, doi: 10.1186/s13634-021-00740-8.

M. F. Fadel, I. D. R. Moses, A. R. Muslikh, and S. W. Iriananda, “Analyzing InceptionV3 and InceptionResNetV2 with Data Augmentation for Rice Leaf Disease Classification,” J. Futur. Artif. Intell. Technol., 2024.

A. Santos, M. Ribeiro, and L. Costa, “Quantitative evaluation metrics for multi-class plant disease classification: A comprehensive analysis,” Unpublished manuscript / Placeholder reference, 2025.

C. J. Hellín, Á. A. Olmedo, A. Valledor, J. Gómez, M. López-Benítez, and A. Tayebi, “Unraveling the impact of class imbalance on deep-learning models for medical image classification,” Appl. Sci., vol. 14, no. 8, p. 3419, 2024, doi: 10.3390/app14083419.

W. Shafik, A. Tufail, C. De Silva Liyanage, and R. A. H. Apong, “Using transfer learning-based plant disease classification and detection for sustainable agriculture ,” BMC Plant Biology , vol. 24. p. 136, 2024.

S. Maheshwari et al., “Redress: generating compressed models for edge inference using tsetlin machines,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 9, pp. 11152–11168, 2023, doi: 10.1109/tpami.2023.3268415.

H. Lu, C. Wang, and Q. Zhang, “Half-UNet: A simplified U-Net architecture for medical image segmentation,” in IEEE/CVF Medical Imaging Conference Proceedings, 2022.

R. K. Rachman, D. R. I. M. Setiadi, A. Susanto, K. Nugroho, and H. M. M. Islam, “Enhanced Vision Transformer and Transfer Learning Approach to Improve Rice Disease Recognition,” J. Comput. Theor. Appl., vol. 1, no. 4, pp. 446–460, 2024, doi: 10.62411/jcta.10459.

S. Wang et al., “Advances in Deep Learning Applications for Plant Disease and Pest Detection: A Review ,” Remote Sensing , vol. 17, no. 4. p. 698, 2025.

X. Chen, Y. Li, and H. Zhang, “Attention-enhanced U-Net for tobacco leaf disease segmentation under complex backgrounds,” Comput. Electron. Agric., vol. 212, p. 108102, 2025.

S. Zhang, J. Li, and Y. Chen, “Modified U-Net for plant diseased leaf image segmentation,” Expert Syst. Appl., vol. 230, p. 120814, 2023, doi: 10.1016/j.eswa.2023.120814.

S. D. R. Team, “A review of InceptionV3 applications in dermoscopy and skin lesion classification,” Sensors, 2024.

R. Sakinah, M. Yusuf, and D. Helmi, “Performance evaluation of VGG16 for plant disease classification,” J. Appl. Image Process., vol. 9, no. 1, pp. 45–56, 2021.

L. Zhang, F. Zhou, and X. Han, “Comprehensive evaluation of VGG-based models for image classification,” IEEE Access, vol. 10, pp. 50112–50125, 2022.

“Visual variability in early-stage plant disease symptoms: Challenges for convolutional neural networks,” Front. Plant Sci., vol. 16, p. 14022, 2025.

T. Archana and S. Jeevaraj, “Plant disease detection using convolutional neural networks: A comprehensive review,” Int. J. Comput. Appl., vol. 182, no. 2, pp. 15–22, 2024.

L. Alzubaidi and et al., “Review of deep learning: Concepts, CNN architectures, challenges, applications, and future directions,” J. Big Data, vol. 8, no. 1, pp. 1–74, 2021.

Z. Yao, “Deep learning in tropical leaf disease detection: advantages and applications,” Trop. Plants, vol. 3, p. Article e020, 2024, doi: 10.48130/tp-0024-0018.