A Deep Learning-Based Framework for Tomato Leaf Disease Classification Using Image Preprocessing and Convolutional Neural Networks
Interdisciplinary Journal of AI, Machine Learning & Data Science · 12.10.2026 · 1 (3) · e011
DOI: 10.66261/hj31hs12 ↗Kurz gefasst
Fachartikel in der Zeitschrift Interdisciplinary Journal of AI, Machine Learning & Data Science, online erschienen am 12.10.2026. Verfasst von Sahil Sher. Die Arbeit nennt 6 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Tomato leaf diseases can reduce crop productivity and quality, motivating automated image-based classification systems. This paper presents an experimentally evaluated convolutional neural network (CNN) framework for ten-class tomato leaf disease classification. The proposed model is a custom CNN consisting of three convolutional layers, three max-pooling layers, ReLU activations, and a fully connected classification head with ten outputs. Convex-hull preprocessing and Otsu thresholding are applied before CNN classification. The dataset contains 18,345 images covering nine disease classes and one healthy class, with 300 images used as the held-out test set. The experimental results report a class-wise average test accuracy of 94.5%. Class-wise precision, recall, and F1-scores are also reported. The training and validation learning curves span approximately 1,000 epochs. The model is compared descriptively with VGG16, InceptionV3, and MobileNet using author-reported baseline results. However, complete dataset-split and hyperparameter information is unavailable for every baseline, preventing a rigorously controlled comparison. The results demonstrate classification performance on the evaluated public dataset, although generalization to independently collected field images remains to be established.
Zitieren
APA
Sher, S. (2026). A Deep Learning-Based Framework for Tomato Leaf Disease Classification Using Image Preprocessing and Convolutional Neural Networks. Interdisciplinary Journal of AI, Machine Learning & Data Science, 1(3), e011. https://doi.org/10.66261/hj31hs12
Vancouver
Sher S. A Deep Learning-Based Framework for Tomato Leaf Disease Classification Using Image Preprocessing and Convolutional Neural Networks. Interdisciplinary Journal of AI, Machine Learning & Data Science. 2026;1(3):e011. doi:10.66261/hj31hs12
BibTeX
@article{Sher2026,
author = {Sher, Sahil},
title = {A Deep Learning-Based Framework for Tomato Leaf Disease Classification Using Image Preprocessing and Convolutional Neural Networks},
journal = {Interdisciplinary Journal of AI, Machine Learning & Data Science},
year = {2026},
volume = {1},
number = {3},
pages = {e011},
doi = {10.66261/hj31hs12}
}
EUVIMED