BD Currency Detection: A CNN Based Approach with Mobile App Integration

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jaman, Syed Jubayer, Haque, Md. Zahurul, Islam, Md Robiul, Noor, Usama Abdun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909509566332928
author Jaman, Syed Jubayer
Haque, Md. Zahurul
Islam, Md Robiul
Noor, Usama Abdun
author_facet Jaman, Syed Jubayer
Haque, Md. Zahurul
Islam, Md Robiul
Noor, Usama Abdun
contents Currency recognition plays a vital role in banking, commerce, and assistive technology for visually impaired individuals. Traditional methods, such as manual verification and optical scanning, often suffer from limitations in accuracy and efficiency. This study introduces an advanced currency recognition system utilizing Convolutional Neural Networks (CNNs) to accurately classify Bangladeshi banknotes. A dataset comprising 50,334 images was collected, preprocessed, and used to train a CNN model optimized for high performance classification. The trained model achieved an accuracy of 98.5%, surpassing conventional image based currency recognition approaches. To enable real time and offline functionality, the model was converted into TensorFlow Lite format and integrated into an Android mobile application. The results highlight the effectiveness of deep learning in currency recognition, providing a fast, secure, and accessible solution that enhances financial transactions and assistive technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17907
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BD Currency Detection: A CNN Based Approach with Mobile App Integration
Jaman, Syed Jubayer
Haque, Md. Zahurul
Islam, Md Robiul
Noor, Usama Abdun
Computer Vision and Pattern Recognition
Machine Learning
Networking and Internet Architecture
Currency recognition plays a vital role in banking, commerce, and assistive technology for visually impaired individuals. Traditional methods, such as manual verification and optical scanning, often suffer from limitations in accuracy and efficiency. This study introduces an advanced currency recognition system utilizing Convolutional Neural Networks (CNNs) to accurately classify Bangladeshi banknotes. A dataset comprising 50,334 images was collected, preprocessed, and used to train a CNN model optimized for high performance classification. The trained model achieved an accuracy of 98.5%, surpassing conventional image based currency recognition approaches. To enable real time and offline functionality, the model was converted into TensorFlow Lite format and integrated into an Android mobile application. The results highlight the effectiveness of deep learning in currency recognition, providing a fast, secure, and accessible solution that enhances financial transactions and assistive technologies.
title BD Currency Detection: A CNN Based Approach with Mobile App Integration
topic Computer Vision and Pattern Recognition
Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2502.17907