Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{182912,
        author = {Natra Veera Mahendra Varma and G. Sharmila Sujatha},
        title = {Cross-Crop Disease Diagnosis: A Deep Learning Model for Leaf Image Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {4042-4048},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182912},
        abstract = {Early and accurate detection of plant diseases is essential for improving crop yield, reducing pesticide overuse, and ensuring food security in agriculture. Traditional methods of disease identification often require expert knowledge, are time-consuming, and may not always be accessible to farmers, especially in rural or resource-limited areas. This study presents an AI-powered plant disease detection system using a custom-designed Convolutional Neural Network (CNN) capable of classifying 39 different types of plant leaf diseases. The model is trained on a diverse and well-labeled image dataset, covering a wide range of disease symptoms across various crops. The CNN architecture is designed to extract complex visual features, enabling it to distinguish between diseases with subtle differences in leaf texture, color, and pattern.
To make the system user-friendly and practical, the trained model is deployed through a Flask-based web application. This interface allows users to upload images of plant leaves, receive instant disease predictions, and view detailed information including symptoms, prevention steps, and recommended treatments or supplements available in the market. The application bridges the gap between advanced machine learning techniques and real-world agricultural needs by providing a simple, accessible tool for non-technical users.
The proposed system demonstrates high classification accuracy during testing, highlighting the effectiveness of deep learning models in agricultural image analysis. Moreover, the integration of prediction results with actionable information makes the tool valuable for farmers, researchers, and agricultural extension workers. This work contributes to the growing field of precision agriculture by showing how AI can be used not only to automate disease recognition but also to support better decision-making in crop management.},
        keywords = {plant disease detection, deep learning, convolutional neural network (cnn), precision agriculture, image classification, smart farming, computer vision, flask web application, agricultural diagnostics, ai in agriculture, crop management, real-time inference, automated disease identification, plant pathology, machine learning deployment.},
        month = {July},
        }