Work

A Hybrid Framework for Real-Time Saudi Riyal Banknote Recognition in Assistive Applications

Year: 2026

Type: article

Abstract: Currency recognition is a vital pillar for the financial independence of visually impaired individuals, yet existing solutions often struggle with the trade-off between architectural complexity and real-time performance. This paper introduces a lightweight hybrid framework specifically engineered for Saudi Riyal banknote identification. The primary contribution lies in the strategic integration of MobileNetV2 for deep feature extraction with a kernel-based Support Vector Machine to enhance classification boundaries. Furthermore, this study addresses a significant data gap by curating an updated dataset that includes the 20 SR denomination, which is largely missing from current public repositories. Methodologically, the framework emphasizes computational efficiency without compromising precision, achieving a robust test accuracy of 98.16. By prioritizing a streamlined architecture, this work provides a scalable and effective solution for mobile-based assistive technologies, fostering greater accessibility and autonomy for the visually impaired community in Saudi Arabia.

Source: Applied Sciences

DOI: 10.3390/app16126166

Authors: Nora Alhammad, Aljawharah Alsubaie, Rama Alomair, Fajer Alamro, Mashael Alammar

Institution: King Saud University

Language: English

Topic: Currency Recognition and Detection

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Reduced inequalities

Open Access status: gold

Estimated APC paid: $2,896