GrapeScan - Grape Leaf Disease Detection
International Journal on Advanced Computer Theory and Engineering · 18.01.2026 · 15 (1S) · 138-145
DOI: 10.65521/ijacte.v15i1s.1312 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal on Advanced Computer Theory and Engineering, online erschienen am 18.01.2026. Verfasst von Akhilesh Sharad Aher und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-ND 4.0).
Abstract (Originalsprache)
Crop yield and quality of grapes are affected adversely by grapevine diseases. Manual inspection of grapes for health and diseases is inefficient due to high volume and potentially high error rates. The authors developed a system called GrapeScan using deep learning algorithms to classify photos of grape leaves into diseased or healthy categories. The system is based on a Convolutional Neural Network (CNN) trained on a publicly available dataset of grape leaves and is available for use in real-time via a web interface. The authors report results indicating that their system has high classification accuracy and low inference time, making it appropriate for use in precision agriculture and other practical farming applications.
Zitieren
APA
Aher, A. S., Sonawane, P. S., Aher, M. D., Sonawane, P. N., & Rajnor, P. D. (2026). GrapeScan - Grape Leaf Disease Detection. International Journal on Advanced Computer Theory and Engineering, 15(1S), 138-145. https://doi.org/10.65521/ijacte.v15i1s.1312
Vancouver
Aher AS, Sonawane PS, Aher MD, Sonawane PN, Rajnor PD. GrapeScan - Grape Leaf Disease Detection. International Journal on Advanced Computer Theory and Engineering. 2026;15(1S):138-145. doi:10.65521/ijacte.v15i1s.1312
BibTeX
@article{Aher2026,
author = {Aher, Akhilesh Sharad and Sonawane, Pravin Subhash and Aher, Mayuresh Dagu and Sonawane, Prathamesh Nitin and Rajnor, Prof. D.S.},
title = {GrapeScan - Grape Leaf Disease Detection},
journal = {International Journal on Advanced Computer Theory and Engineering},
year = {2026},
volume = {15},
number = {1S},
pages = {138--145},
doi = {10.65521/ijacte.v15i1s.1312}
}
EUVIMED