Robust Maturity Level Classification of Bell Pepper using CNN
International Journal of Informatics and Computation · 25.07.2025 · 7 (2) · 330-337
DOI: 10.35842/ijicom.v7i2.139 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Informatics and Computation, online erschienen am 25.07.2025. Verfasst von Rino Aziz Fadhillah und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
The development of artificial intelligence has opened up new opportunities in various fields, including Bell Pepper image detection. The remaining issues are that the selection of the ripeness level of bell peppers manually can take a long time and requires more accuracy. The purpose of this research is to classify the maturity level of bell peppers and to determine the level of accuracy. The research method used is Convolutional Neural Network (CNN) with tools or tools, namely Visual Studio Code in Python with TensorFlow Framework, as well as a pre-trained CNN architecture called VGG16. Bell peppers are divided into 3 levels of ripeness with different types of colors: green (unripe), yellow (half-ripe), and red (ripe). The results showed that in classifying the maturity level of bell peppers with an accuracy of 89%, precision 84%, recall of 83%, and F1-Score of 84%.
Zitieren
APA
Fadhillah, R. A., & Irwansyah, I. (2025). Robust Maturity Level Classification of Bell Pepper using CNN. International Journal of Informatics and Computation, 7(2), 330-337. https://doi.org/10.35842/ijicom.v7i2.139
Vancouver
Fadhillah RA, Irwansyah I. Robust Maturity Level Classification of Bell Pepper using CNN. International Journal of Informatics and Computation. 2025;7(2):330-337. doi:10.35842/ijicom.v7i2.139
BibTeX
@article{Fadhillah2025,
author = {Fadhillah, Rino Aziz and Irwansyah, Irwansyah},
title = {Robust Maturity Level Classification of Bell Pepper using CNN},
journal = {International Journal of Informatics and Computation},
year = {2025},
volume = {7},
number = {2},
pages = {330--337},
doi = {10.35842/ijicom.v7i2.139}
}
EUVIMED