Automated Leaf Disease Detection Using Recurrent Convolutional Neural Networks

DOI

10.2991/978-94-6463-866-0_52How to use a DOI?

Keywords

Deep learning; RCNN; RNN; GRU; AdamW; ReLU; Linear Unit; SWISH

Abstract

The presence of diseases in plant leaves poses a serious challenge to agricultural productivity, often leading to considerable financial losses. Identifying and diagnosing these diseases at an early stage is essential for effective crop management. This study introduces an advanced method for automated leaf disease detection using a Recurrent Convolutional Neural Network (RCNN) instead of traditional CNN-based models. RCNN allows wider range of inputs with consistent predictions, not always requiring ideal conditions of the image either. The model has been developed using a diverse dataset sourced from PlantVillage, Kaggle, and Google Images, ensuring a broad and well-balanced training foundation.

To achieve an optimal balance between accuracy and computational efficiency, the Model architecture has been fine-tuned, resulting in an accuracy of 95.32% in non-ideal conditions, images captured by cameras of mobile phones in different environments like rain, sunlight, dry conditions, with different lighting conditions each.

Users can conveniently upload apple leaf images via a web-based interface, where the trained model swiftly analyzes the images and predicts the disease category. For enhanced accessibility, the detection system has been seamlessly integrated into a Flask-powered web application, making it easily usable for farmers and agricultural professionals. Comparative analysis reveals that this approach outperforms conventional machine learning models. Looking ahead, future enhancements will focus on expanding this system into mobile platforms and integrating it with IoT-driven smart farming technologies to facilitate real-time, scalable disease detection.

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  - Avadhoot Rajurkar
AU  - Aman Ayubkhan Pathan
AU  - Akshit Rai
AU  - Anvi Doshi
AU  - Angelina Anthony
AU  - Sanika Akulwar
AU  - Arya Ambekar
PY  - 2025
DA  - 2025/10/31
TI  - Automated Leaf Disease Detection Using Recurrent Convolutional Neural Networks
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 629
EP  - 641
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_52
DO  - 10.2991/978-94-6463-866-0_52
ID  - Rajurkar2025
ER  -