Published Paper Details:

Abstract: Agriculture is a vital industry that supports the global economy, and plant diseases are a significant threat to crop productivity and food security. Quickly and accurately identifying plant diseases is crucial for effective treatment and prevention. Traditional methods of detecting diseases depend on manual observation and expert knowledge. These methods can be slow, subjective, and prone to mistakes. To tackle these issues, this research introduces an automated plant disease detection system that uses deep learning techniques. The proposed model uses Convolutional Neural Networks (CNN) to extract features and classify diseased and healthy plant leaves. The dataset includes images of various crop leaves affected by different diseases. We apply image preprocessing techniques like resizing, normalization, and data augmentation to improve the model's performance. Additionally, using pre-trained architectures like ResNet for transfer learning boosts accuracy and lowers computational costs. The trained model shows high precision and recall, proving its ability to identify multiple disease types with minimal human input. Experimental results demonstrate that this approach greatly surpasses traditional machine learning methods in classification accuracy and generalization. This work shows how deep learning-based systems can help farmers and agricultural experts detect diseases early, which can enhance crop yield and reduce losses. Future work plans to integrate the model into a mobile application for real-time disease identification and field use.