Plant Leaf Disease Classification Using Convolutional Neural Networks (CNN)

Afrin Akhtar, Mithlesh Kumar, Dr. Gargi Shankar Verma

Abstract: Plant disease significantly affects agricultural productivity and crop quality. Traditional detection method relies on manual inspection, which is time consuming and prone to inaccuracies. Recent advancement in deep learning have enabled automated disease detection using image-based approaches [1] [2]. This paper presents a Convolutional Neural Network (CNN) based system for Plant Leaf Disease Detection. The model trained on a structured dataset using preprocessing and augmentation technique to improve generalization and reduce overfitting [3]. This study presents a lightweight Convolutional Neural Network (CNN) model for automated Plant Leaf Disease Classification using image data. Traditional detection methods rely on manual inspection, which is time-consuming and prone to error. The proposed model incorporates preprocessing and data augmentation techniques to improve generalization and reduce overfitting. Experimental results demonstrate that the model achieves approximately 85% accuracy with stable convergence and minimal overfitting. The system supports real-time prediction and is suitable for practical agricultural applications. The findings highlight the effectiveness of CNN-based approaches for scalable and efficient plant disease detection. The proposed system supports real-time prediction making it suitable for practical agricultural applications.

Keywords: CNN, Plant disease detection, deep learning, image classification, precision agriculture

How to Cite?: Afrin Akhtar, Mithlesh Kumar, Dr. Gargi Shankar Verma, "Plant Leaf Disease Classification Using Convolutional Neural Networks (CNN)", Volume 15 Issue 5, May 2026, International Journal of Science and Research (IJSR), Pages: 289-294, https://www.ijsr.net/getabstract.php?paperid=SR26504141606, DOI: https://dx.dx.doi.org/10.21275/SR26504141606

Download Citation: APA | MLA | BibTeX | EndNote | RefMan