Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190530,
        author = {Karthika E S and Rohith M R and Sabarinadh M M and Sidharth E S and Ms Priya K P and Ms Anooja V S},
        title = {A Comprehensive Review of Currency Detection Techniques for Assisting Visually Impaired Individuals Using Raspberry Pi},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {3757-3761},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190530},
        abstract = {Visually impaired individuals face significant challenges in identifying currency denominations during routine financial transactions, often resulting in dependency on others and increased vulnerability to fraud. The absence of reliable tactile cues across different currencies further complicates the process. With rapid advancements in artificial intelligence, computer vision, deep learning, embedded systems, and Internet of Things (IoT) technologies, intelligent currency detection systems have emerged as effective assistive solutions. These systems typically employ camera-based image acquisition, deep learning-based classification, and real-time audio feedback to convey denomination information to users. This paper presents a comprehensive literature review of currency detection techniques developed for visually impaired people, focusing on deep learning-based methods, lightweight architectures for edge devices, Raspberry Pi-based implementations, and multimodal assistive frameworks. The review analyzes methodologies, system architectures, performance metrics, and hardware platforms reported in recent literature. Although existing approaches demonstrate promising accuracy and portability, challenges such as illumination variation, worn or folded banknotes, multi-currency support, dataset limitations, and real-world deployment persist. This paper synthesizes current research trends, identifies critical gaps, and outlines future research directions toward robust, scalable, and cost-effective assistive currency detection systems.},
        keywords = {Currency recognition, currency detection, banknote recognition, assistive technology, visually impaired assistance, computer vision, deep learning, convolutional neural networks, lightweight neural networks, edge computing, embedded systems, Raspberry Pi, real-time image processing, audio feedback systems, text-to-speech},
        month = {January},
        }