Performance Comparison of CNN Transfer Learning Models for Coffee Bean Quality Classification
Jurnal Teknologi Informasi dan Terapan · 31.12.2025 · 12 (2) · 95-104
DOI: 10.25047/jtit.v12i2.457 ↗Kurz gefasst
Fachartikel in der Zeitschrift Jurnal Teknologi Informasi dan Terapan, online erschienen am 31.12.2025. Verfasst von Nur Muhammad Fadli und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
According to SNI Standard No. 01-2907-2008, accurate sorting of coffee beans is crucial for improving export value. Manual sorting is time-consuming, subjective, and error-prone, especially when visual differences are subtle between roast levels. This study proposes and evaluates an automatic, machine-learning based system to support quality assurance in coffee production. We compare three transfer-learning CNN architectures: Xception, MobileNetV2, and EfficientNet-B1 on a publicly available dataset of 1,600 coffee bean images divided into four classes (dark, medium, light, green). All models were trained with the same preprocessing and hyperparameter settings. EfficientNet-B1 achieved the highest test accuracy (100%), followed by Xception (99.5%) and MobileNetV2 (97%). We discuss trade-offs between accuracy and computational efficiency and recommend EfficientNet-B1 for high-accuracy applications and MobileNetV2 for edge/mobile deployment.
Zitieren
APA
Fadli, N. M., Destarianto, P., Riskiawan, H. Y., Susanto, B. M., Priyambada, S. A., Nur, W. H., & Gumilang, M. A. (2025). Performance Comparison of CNN Transfer Learning Models for Coffee Bean Quality Classification. Jurnal Teknologi Informasi dan Terapan, 12(2), 95-104. https://doi.org/10.25047/jtit.v12i2.457
Vancouver
Fadli NM, Destarianto P, Riskiawan HY, Susanto BM, Priyambada SA, Nur WH, et al. Performance Comparison of CNN Transfer Learning Models for Coffee Bean Quality Classification. Jurnal Teknologi Informasi dan Terapan. 2025;12(2):95-104. doi:10.25047/jtit.v12i2.457
BibTeX
@article{Fadli2025,
author = {Fadli, Nur Muhammad and Destarianto, Prawidya and Riskiawan, Hendra Yufit and Susanto, Bekti Maryuni and Priyambada, Satrio Adi and Nur, Wawan Hendriawan and Gumilang, Mukhamad Angga},
title = {Performance Comparison of CNN Transfer Learning Models for Coffee Bean Quality Classification},
journal = {Jurnal Teknologi Informasi dan Terapan},
year = {2025},
volume = {12},
number = {2},
pages = {95--104},
doi = {10.25047/jtit.v12i2.457}
}
EUVIMED