AI-Driven Feature Extraction for Jute Leaf Disease Detection Using Enhanced Deep Learning

DOI

10.2991/978-94-6239-664-7_50How to use a DOI?

Keywords

Jute leaf disease; Plant pathology; Transfer learning; Image classification

Abstract

The application of intelligent image analysis in agriculture has improved early detection of plant diseases, helping prevent yield losses and limit infection spread. Jute, an important cash crop in Bangladesh, serves as an environmentally friendly raw material but is highly susceptible to leaf diseases such as cercospora leaf spot and golden mosaic disease, which reduce crop quality and yield. Despite advances in automated plant disease detection, limited research applies deep learning to jute leaf disease classification. Images showing symptoms of the two main diseases were grouped into a single diseased class for a binary classification task. This study addresses limitations of computationally complex ensemble methods by proposing an Enhanced ResNet50 model built on a pre-trained ResNet50 with additional convolutional, pooling, and dense layers for improved feature extraction and classification performance. The model was trained and evaluated on a curated dataset of 920 jute leaf images and compared with VGG16, VGG19, ResNet50, InceptionV3, and recent literature methods. The Enhanced ResNet50 achieved a high accuracy of 99.51% and demonstrated robustness and reliability through precision, recall, F1-score, and confusion matrix analysis. This approach enables early jute disease detection, supporting sustainable agriculture in Bangladesh. Future work includes external validation, interpretability analysis, and assessment on early-stage or mixed disease symptoms.

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. Minhajul Islam
AU  - Md. Didar Ahmed
AU  - Abdullah Al Mamun
AU  - Pollob Chandra Ray
AU  - Md. Mithun Ali
PY  - 2026
DA  - 2026/06/08
TI  - AI-Driven Feature Extraction for Jute Leaf Disease Detection Using Enhanced Deep Learning
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 719
EP  - 732
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_50
DO  - 10.2991/978-94-6239-664-7_50
ID  - Islam2026
ER  -