Image‐Feature Based Deep Learning Model for Plant Leaf Disease Detection
Macromolecular Symposia · 2024-02 · 413 (1)
DOI: 10.1002/masy.202200216 ↗Kurz gefasst
Fachartikel in der Zeitschrift Macromolecular Symposia, online erschienen am 21.02.2024. Verfasst von Lekha Rani und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 11 Literaturangaben.
Abstract (Originalsprache)
Currently, everyone is facing significant difficulties with food scarcity. There may be several causes for this, but food loss is a well‐known issue. Specifically, crop losses bring on by plant and leaf diseases during farming operations. Plant disease is typically identified visually or through laboratory testing, which delays detection and reduces crop yields by the time it is finished. The wide use of smartphones along with recent advancements in computer vision has made it viable to diagnose any ailment by applying machine learning techniques. Smartphone‐assisted disease diagnosis is now a reality. In this study, a multi‐Support Vector Machine (SVM) model is used to detect four different diseases as well as healthy conditions of plant leaves. Using 13 feature vectors for each input, a total of 2400 leaves representing four distinct classes (four varieties) have been used to train and test the model. The experimental results give an average accuracy of 91.25% for diseased leaves detection and 99% accuracy for healthy leaves detection.
Zitieren
APA
Rani, L., Sarangi, P. K., & Sahoo, A. K. (2024). Image‐Feature Based Deep Learning Model for Plant Leaf Disease Detection. Macromolecular Symposia, 413(1). https://doi.org/10.1002/masy.202200216
Vancouver
Rani L, Sarangi PK, Sahoo AK. Image‐Feature Based Deep Learning Model for Plant Leaf Disease Detection. Macromolecular Symposia. 2024;413(1). doi:10.1002/masy.202200216
BibTeX
@article{Rani2024,
author = {Rani, Lekha and Sarangi, Pradeepta Kumar and Sahoo, Ashok Kumar},
title = {Image‐Feature Based Deep Learning Model for Plant Leaf Disease Detection},
journal = {Macromolecular Symposia},
year = {2024},
volume = {413},
number = {1},
doi = {10.1002/masy.202200216}
}
EUVIMED