Transformer-Based Approach for Jute Leaf Disease Detection and Classification

DOI

10.2991/978-94-6239-664-7_56How to use a DOI?

Keywords

Cercospora; Phosphorus Deficiency; Vision Transformer; Swin Transformer; ConvNeXt

Abstract

Jute (Corchorus spp.) is one of the most important fibre crops for Bangladesh and many tropical countries. However, its production often suffers from leaf diseases such as insect holes, yellowing, Cercospora leaf spot, and phosphorus deficiency. Farmers usually identify these problems by visual inspection, which can be slow and sometimes inaccurate. In this work, we developed and tested a machine learning system that can classify jute leaf conditions from images. Our dataset contained 2,620 original field images across five categories, which we expanded to 17,500 images through augmentation to improve balance and robustness. We compared several models, including Vision Transformer, ConvNeXt, Swin Transformer, MobileNet, DenseNet121, VGG, and graph-based hybrids. The Vision Transformer model gave the best results, reaching 99.85% validation accuracy and high precision, recall, and F1-scores, followed closely by ConvNeXt and Swin Transformer. These findings suggest that transformer-based networks can reliably detect jute leaf diseases, making them suitable for practical tools such as mobile-based early warning systems for farmers.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Md. Hasanuzzaman Dipu
AU  - Noman Mezi
AU  - Ahmad Kamal
AU  - Sumaiya Khanam
AU  - Sheak Rashed Haider Noori
AU  - M. Humayet Islam
PY  - 2026
DA  - 2026/06/08
TI  - Transformer-Based Approach for Jute Leaf Disease Detection and Classification
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 813
EP  - 826
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_56
DO  - 10.2991/978-94-6239-664-7_56
ID  - Dipu2026
ER  -