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{190647,
        author = {V. Kavitha and S.Jayananthini ME},
        title = {PLANT LEAF DISEASE DETECTION USING MACHINE LEARNING AND DEEP LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {4392-4399},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190647},
        abstract = {Plant diseases significantly reduce agricultural productivity, leading to lower crop quality and major economic losses worldwide. Early and accurate identification of leaf diseases is essential for effective crop management and timely intervention. Traditional manual inspection is slow, labor-intensive, and prone to errors, creating a strong need for automated and intelligent disease detection systems. Advances in machine learning and deep learning now enable fast and reliable image-based diagnosis for precision agriculture.
This study proposes an automated plant leaf disease detection framework using both classical machine learning algorithms and deep learning techniques. A curated dataset of leaf images is preprocessed through resizing, noise removal, augmentation, and segmentation to improve model performance. Classical models such as SVM, Random Forest, k-NN, and Logistic Regression are trained using handcrafted features derived from color, texture, and shape descriptors.
To achieve higher accuracy, a Convolutional Neural Network (CNN) is incorporated to automatically learn hierarchical image features. The CNN consists of convolutional, pooling, and fully connected layers, optimized with dropout, batch normalization, the Adam optimizer, and learning-rate scheduling. Comparative analysis shows that the CNN significantly outperforms traditional models in both accuracy and generalization.
Extensive experiments using accuracy, precision, recall, F1-score, and confusion matrices confirm the effectiveness of the proposed approach. The CNN accurately classifies common plant diseases—including bacterial blight, leaf spot, mildew, and rust—across various species. Cross-validation and testing on unseen images further demonstrate the model’s robustness and deployment readiness.
Overall, the system provides a fast, reliable, and scalable tool for farmers and agronomists. With support for real-time mobile or web-based deployment, it offers a practical solution for large-scale agricultural monitoring. The study highlights that combining classical machine learning with deep learning, especially CNNs, greatly enhances plant disease detection, enabling smarter and more sustainable crop management.},
        keywords = {Deep Learning, Leaf Disease, Plant Disease Detection, Image Processing, Neural Classification Network, ENCN, Support Vector Machine, SVM},
        month = {January},
        }