Diseases in tomato, potato, and pepper crops cause significant losses for farmers, often requiring laborious manual monitoring. A team of researchers led by Vijaya Saraswathi, a teacher-researcher at VNR Vignana Jyothi Institute of Engineering and Technology in Hyderabad, has developed an AI-powered leaf disease detection system to address this problem, according to a report in The Hindu BusinessLine.
The Problem of Plant Leaf Diseases
Leaf diseases, caused by pests, fungi, and bacteria, pose a serious threat to food security by destroying crops from the top and bottom. Traditionally, spotting these diseases requires continuous, laborious monitoring. To prevent heavy losses and boost yields, early and automated detection has become vital. Saraswathi, drawing on decades of watching her father struggle with crop losses, set out to find a solution.
AI-Powered Solution Using CNN
The team built their work on a Kaggle PlantVillage dataset that contained over 20,000 images. They trained a Convolutional Neural Network (CNN) model using standard image processing, feature extraction, and segmentation steps. The system automatically suggests the right pesticide to resolve the identified disease, going beyond mere detection.
“Early and accurate disease identification can help farmers make informed decisions, optimise pesticide usage, and enhance agricultural productivity,” Saraswathi said.
“This solution reflects how AI and deep learning are being applied to solve real-world agricultural challenges,” she added.
Patent and 96% Accuracy
| Feature | Detail |
|---|---|
| Dataset | Kaggle PlantVillage (20,000+ images) |
| Model | Convolutional Neural Network (CNN) |
| Accuracy | 96% |
| Patent Name | “Leaf Disease Detection System Using Convolutional Neural Networks” |
| Patent Timeline | Work started in 2022, entered patent process in 2023, approved April 2026 |
The system stands apart from existing systems by scoring a 96% accuracy rate, according to the researchers. The work started in 2022, entered the patent process in 2023, and received approval in April 2026. “Our solution stands apart from existing systems by scoring a 96% accuracy rate,” Saraswathi told businessline.
Mobile App Development Planned
Currently, the system is available through a web interface. The team is planning to build a mobile app to make it much more accessible for farmers. The solution aims to help farmers catch plant diseases early, preventing heavy harvests from going to waste.
For enterprise technology decision-makers, this development demonstrates how AI and deep learning can be applied to agricultural supply chains — from crop monitoring to pesticide optimisation — potentially reducing losses and improving yield predictability. The use of a CNN on a publicly available dataset and the planned mobile deployment highlight a low-barrier path to field deployment for similar AI-driven diagnostics.
Sources: