A Hybrid Framework for Real-Time Saudi Riyal Banknote Recognition in Assistive Applications
Source abstract
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: crossref · Quality: baseline
Research context
OpenAlex topics: Currency Recognition and Detection · Handwritten Text Recognition Techniques · Big Data and Digital Economy
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer and Information Sciences, King Saud University, Riyadh 11451, Saudi Arabia
Funding
King Saud University, Riyadh, Saudi Arabia
References (25)
Show source-provided references
1. World Health Organization (2019). World Report on Vision, WHO.
2. General Authority for Statistics (2022). Population and Housing Census 2022.
3. Saudi Arabian Monetary Authority (2026, January 01). Saudi Currency, Available online: https://www.sama.gov.sa.
4. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–23 June 2018, IEEE.10.1109/CVPR.2018.00474 ↗
5. Saudi Riyal Banknote Recognition System Using Color Features
6. AlFloos: A Balanced Dataset for the Sixth Issue of the Saudi Arabian Currency Banknote10.1007/s43995-024-00067-z ↗
7. A Novel Method for Banknote Recognition Using SURF Detector with SIFT and HOG Features
8. Rajput, G.K., Mali, S.M., and Patil, R. (2019). Indian Currency Recognition Using Deep Learning. Proceedings of the International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 15–17 May 2019, IEEE.
9. Rupiah Banknote Classification Using MobileNetV2 Based on Image Data
10. Smart Rupiah Recognition: A Mobile Machine Learning Approach for Visually Impaired Users
11. Ethiopian Banknote Recognition Using Convolutional Neural Network and Its Prototype Development Using Embedded Platform10.1155/2022/4505089 ↗
12. Park, C., and Park, K.R. (2023). MBDM: Multinational Banknote Detecting Model for Assisting Visually Impaired People. Mathematics, 11.10.3390/math11061392 ↗
13. Recognizing Egyptian Currency for People with Visual Impairment Using Deep Learning Models10.1038/s41598-025-20646-x ↗
14. A Comprehensive Survey on Transfer Learning10.1109/JPROC.2020.3004555 ↗
15. Razavian, A.S., Azizpour, H., Sullivan, J., and Carlsson, S. (2014). CNN Features Off-the-Shelf: An Astounding Baseline for Recognition. Proceedings of the IEEE CVPR Workshops, Columbus, OH, USA, 23–28 June 2014, IEEE.10.1109/CVPRW.2014.131 ↗
16. Support-Vector Networks10.1023/A:1022627411411 ↗
17. Do We Need Hundreds of Classifiers to Solve Real World Classification Problems?
18. A Survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
19. A Systematic Study of the Class Imbalance Problem in Convolutional Neural Networks10.1016/j.neunet.2018.07.011 ↗
20. Zauner, C. (2010). Implementation and Benchmarking of Perceptual Image Hash Functions. [Master’s Thesis, University of Applied Sciences Upper Austria].
21. (2026, January 01). Saudi Currencies Object Detection Model, Version 5. Available online: https://universe.roboflow.com/workspace/saudi_currencies-4ipct/model/5.
22. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Li, F.-F. (2009). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA, 20–25 June 2009, IEEE.10.1109/CVPR.2009.5206848 ↗
23. Comparative Analysis of Cross-Validation Techniques: LOOCV, K-folds Cross-Validation, and Repeated K-folds Cross-Validation in Machine Learning Models10.11648/j.ajtas.20241305.13 ↗
24. A Systematic Analysis of Performance Measures for Classification Tasks10.1016/j.ipm.2009.03.002 ↗
25. Bouthillier, X., Laurent, C., and Vincent, P. (2019, January 9–15). Unreproducible Research is Reproducible. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA.