Paper Contents
Abstract
Plant diseases are a major threat to world agricultural production, causing economic losses and food shortages. Manualinspection or the conventional method of disease detection is time-consuming, inefficient, and inaccurate. In this work, wepresent a Convolutional Neural Network (CNN) approach for computer-aided plant disease detection from leaf images. The work uses the New Plant Diseases Dataset on Kaggle, which consists of several classes of healthy and diseased leaf images. The data is preprocessed through resizing, normalization, and augmentation to improve model performance. A deep CNN model is trained and tested with standard evaluation metrics like accuracy, precision, recall, and F1-score. Experimental results show that our model performs well in classification accuracy compared to conventional old and physical techniques. This research helps to improve AI-based agricultural diagnostics, allowing farmers to diagnose plant diseases effectively and adapt timely preventive actions. Future research involves improving model accuracy and robustness through transfer learning and applying the model for real-time disease detection.
Copyright
Copyright © 2025 Apurva M. Bhavsar. This is an open access article distributed under the Creative Commons Attribution License.
