RUPIAHVISION: INTRODUCTION TO MOBILENETV2-BASED RUPIAH FOR THE VISUALLY IMPAIRED AND REAL-WORLD PERFORMANCE GAPS
TECHNOVATAR Jurnal Teknologi, Industri, dan Informasi · 17.11.2026 · 5 (1) · 1-11
DOI: 10.61434/technovatar.v5i1.444 ↗Kurz gefasst
Fachartikel in der Zeitschrift TECHNOVATAR Jurnal Teknologi, Industri, dan Informasi, online erschienen am 17.11.2026. Verfasst von Ahmad Ngiliyun und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Visually impaired people often cannot distinguish Rupiah banknote denominations, and classifiers that score well on internal test data may still fail on everyday photographs. This study built RupiahVision, a mobile Rupiah recognizer, and measured the gap between internal and real-world performance. A pretrained MobileNetV2 with a frozen backbone and an eight-class head was trained on 3,173 images combining a public Kaggle dataset with the team's photographs, then served through FastAPI to a React Native application. Evaluation used 485 internal test images and 259 separately prepared real-world photographs. Internal accuracy reached 92.99%, whereas real-world accuracy was only 48.65%. Errors concentrated on the Rp2,000 prediction (91 of 259 predictions) and Rp20,000, while the non-banknote class kept a recall of 0.95. Internal accuracy alone therefore cannot establish readiness; training data diversity and consistent preprocessing at serving time should be prioritized.
Zitieren
APA
Ngiliyun, A., Subakti, I., Sucipto, R. A., Febrianto, N., & Nurfitriani, I. (2026). RUPIAHVISION: INTRODUCTION TO MOBILENETV2-BASED RUPIAH FOR THE VISUALLY IMPAIRED AND REAL-WORLD PERFORMANCE GAPS. TECHNOVATAR Jurnal Teknologi, Industri, dan Informasi, 5(1), 1-11. https://doi.org/10.61434/technovatar.v5i1.444
Vancouver
Ngiliyun A, Subakti I, Sucipto RA, Febrianto N, Nurfitriani I. RUPIAHVISION: INTRODUCTION TO MOBILENETV2-BASED RUPIAH FOR THE VISUALLY IMPAIRED AND REAL-WORLD PERFORMANCE GAPS. TECHNOVATAR Jurnal Teknologi, Industri, dan Informasi. 2026;5(1):1-11. doi:10.61434/technovatar.v5i1.444
BibTeX
@article{Ngiliyun2026,
author = {Ngiliyun, Ahmad and Subakti, Irfan and Sucipto, Rendi Agus and Febrianto, Nikolas and Nurfitriani, Ika},
title = {RUPIAHVISION: INTRODUCTION TO MOBILENETV2-BASED RUPIAH FOR THE VISUALLY IMPAIRED AND REAL-WORLD PERFORMANCE GAPS},
journal = {TECHNOVATAR Jurnal Teknologi, Industri, dan Informasi},
year = {2026},
volume = {5},
number = {1},
pages = {1--11},
doi = {10.61434/technovatar.v5i1.444}
}
EUVIMED