用CNN识别孟加拉国钞票，准确率达98.5%。
BD Currency Detection: A CNN Based Approach with Mobile App Integration
- 基于CNN构建钞票分类模型，使用5万张图像训练
- 模型准确率达98.5%，优于传统方法
- 已集成到安卓应用，支持离线实时识别
货币识别在银行、商业及视障人士辅助技术中至关重要。传统方法如人工核验和光学扫描常因准确率与效率不足而受限。本研究提出一种基于卷积神经网络（CNN）的先进货币识别系统，用于精准分类孟加拉国钞票。收集并预处理了包含50,334张图像的数据集，用于训练高性能分类的CNN模型。训练后的模型准确率达到98.5%，超越传统基于图像的货币识别方法。为实现实时与离线功能，模型被转换为TensorFlow Lite格式，并集成至安卓移动应用。结果表明深度学习在货币识别中的有效性，提供了一种快速、安全且易访问的解决方案，有助于提升金融交易与辅助技术体验。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。