A Smart Rice Leaf Disease Prediction Using Swin Transformer

DOI

10.2991/978-94-6463-858-5_100How to use a DOI?

Keywords

deep learning; Swin Transformer; CNN; ViT

Abstract

Rice is one of the most widely farmed grain crops and a key food source in India. According to FAO, 50% more food will be required by 2050 to support the increasing global population. For the country, rice exports contribute to India’s foreign exchange earnings. Disease damage to rice can significantly diminish production. Every year, Plant diseases and pests cause 20% to 40% of crops to be lost. Plant diseases, which impact the vast majority of food crops in agriculture, are one of the most serious threats to food security. Rice leaf diseases can cause economic losses due to lower yields and higher production expenses. Detection of rice leaf diseases earlier can prevent the spread of diseases, enhance crop yields, and prevent economic losses. Image classification has been transformed by deep learning. In order to classify rice leaf diseases, we use a Swin Transformer, a cutting-edge Vision Transformer (ViT) model. Swin Transformer, a deep learning technique that rapidly and hierarchically processes pictures, is the foundation of this model for identifying and detecting rice plant diseases. This model uses self-attention mechanisms to aquire the leaf images’ local and global features in contrast to conventional CNN-based techniques. The model effectively classifies images of rice leaves into four groups following feature extraction and classification: Healthy, Brown Spot, Hispa, and Leaf Blast. This model effectively classifies the rice leaf diseases with an accuracy of 98.21%.

Copyright

© 2025 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  - S. Arthy
AU  - P. S. Abarna
AU  - S. Padma Priya
AU  - G. Sakthi Priya
PY  - 2025
DA  - 2025/11/04
TI  - A Smart Rice Leaf Disease Prediction Using Swin Transformer
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 1204
EP  - 1213
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_100
DO  - 10.2991/978-94-6463-858-5_100
ID  - Arthy2025
ER  -