Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Real-Time Currency Detection and Voice Feedback for Visually Impaired Individuals

Saraf Anzum Shreya, MD. Abu Ismail Siddique, Sharaf Tasnim

TL;DR

The paper addresses real-time currency recognition to aid visually impaired users by leveraging smartphone cameras and machine learning. It introduces a YOLOv8n-based detector with a custom detection head that incorporates Squeeze-and-Excitation blocks, trained on USD, EUR, and BDT to classify 30 currency classes, achieving high accuracy and fast inference. The system delivers real-time voice feedback and is demonstrated against standard YOLOv8n and prior studies, with reported metrics including $Accuracy\approx97.73\%$, $Recall\approx95.23\%$, $F1\approx95.85\%$, and $mAP@IoU=0.5\approx97.21\%$, at ~3.1 ms per image. While effective for on-device currency recognition and accessibility, the work notes limitations such as the absence of counterfeit detection and suggests future expansion to more currencies, offline deployment, and integrated authenticity checks to broaden practical impact.

Abstract

Technologies like smartphones have become an essential in our daily lives. It has made accessible to everyone including visually impaired individuals. With the use of smartphone cameras, image capturing and processing have become more convenient. With the use of smartphones and machine learning, the life of visually impaired can be made a little easier. Daily tasks such as handling money without relying on someone can be troublesome for them. For that purpose this paper presents a real-time currency detection system designed to assist visually impaired individuals. The proposed model is trained on a dataset containing 30 classes of notes and coins, representing 3 types of currency: US dollar (USD), Euro (EUR), and Bangladeshi taka (BDT). Our approach uses a YOLOv8 nano model with a custom detection head featuring deep convolutional layers and Squeeze-and-Excitation blocks to enhance feature extraction and detection accuracy. Our model has achieved a higher accuracy of 97.73%, recall of 95.23%, f1-score of 95.85% and a mean Average Precision at IoU=0.5 (mAP50(B)) of 97.21\%. Using the voice feedback after the detection would help the visually impaired to identify the currency. This paper aims to create a practical and efficient currency detection system to empower visually impaired individuals independent in handling money.

Real-Time Currency Detection and Voice Feedback for Visually Impaired Individuals

TL;DR

The paper addresses real-time currency recognition to aid visually impaired users by leveraging smartphone cameras and machine learning. It introduces a YOLOv8n-based detector with a custom detection head that incorporates Squeeze-and-Excitation blocks, trained on USD, EUR, and BDT to classify 30 currency classes, achieving high accuracy and fast inference. The system delivers real-time voice feedback and is demonstrated against standard YOLOv8n and prior studies, with reported metrics including , , , and , at ~3.1 ms per image. While effective for on-device currency recognition and accessibility, the work notes limitations such as the absence of counterfeit detection and suggests future expansion to more currencies, offline deployment, and integrated authenticity checks to broaden practical impact.

Abstract

Technologies like smartphones have become an essential in our daily lives. It has made accessible to everyone including visually impaired individuals. With the use of smartphone cameras, image capturing and processing have become more convenient. With the use of smartphones and machine learning, the life of visually impaired can be made a little easier. Daily tasks such as handling money without relying on someone can be troublesome for them. For that purpose this paper presents a real-time currency detection system designed to assist visually impaired individuals. The proposed model is trained on a dataset containing 30 classes of notes and coins, representing 3 types of currency: US dollar (USD), Euro (EUR), and Bangladeshi taka (BDT). Our approach uses a YOLOv8 nano model with a custom detection head featuring deep convolutional layers and Squeeze-and-Excitation blocks to enhance feature extraction and detection accuracy. Our model has achieved a higher accuracy of 97.73%, recall of 95.23%, f1-score of 95.85% and a mean Average Precision at IoU=0.5 (mAP50(B)) of 97.21\%. Using the voice feedback after the detection would help the visually impaired to identify the currency. This paper aims to create a practical and efficient currency detection system to empower visually impaired individuals independent in handling money.
Paper Structure (33 sections, 12 equations, 8 figures, 5 tables)

This paper contains 33 sections, 12 equations, 8 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Materials & Methods
  4. Overflow of Proposed Method
  5. Data Acquisition
  6. Data Preparation
  7. Data Preprocessing
  8. Gaussian Blurring
  9. CLAHE (Contrast Limited Adaptive Histogram Equalization)
  10. Image Sharpening
  11. Preprocessing Pipeline
  12. Model Architecture
  13. Custom Modifications to the Model
  14. Squeeze-and-Excitation (SE) Block
  15. Custom Detection Head
  16. ...and 18 more sections

Figures (8)

  • Figure 1: Overflow of the Process
  • Figure 2: Sample images from the dataset with different backgrounds and lightings.
  • Figure 3: Sample images from the dataset with annotations.
  • Figure 4: Sample images of the preprocessing pipeline showing (from left to right) the original image, Gaussian blurred image, CLAHE-enhanced image and sharpened image.
  • Figure 5: Structure of the Custom Detection Head.
  • ...and 3 more figures