Scholarlink

Despite a global shift toward digital payments, counterfeit banknotes remain a significant issue due to the continued use of paper currency. In India, the Reserve Bank of India (RBI) faces substantial challenges in identifying counterfeit notes amid evolving counterfeiting techniques. We created a CNN-based model to detect counterfeit Indian rupee bills worth ₹50, ₹100, ₹500, and ₹2000. Trained on a comprehensive dataset of top-notch banknote images, it reached an impressive 98% accuracy in tests and 99% during training. This model operates with increased speed and accuracy for real-time detection compared to conventional methods. Connecting this model to systems of the Reserve Bank of India (RBI) can enhance the efficiency of counterfeit currency detection, leading to savings in time and resources. This novel method provides a contemporary answer that is faster and more accurate than earlier approaches. It has the potential to completely change the RBI's management of counterfeit detection by optimizing operational workflows and the detection process itself if it is integrated with the RBI's present systems. Our future work will concentrate on extending the model's use to additional currencies and enhancing its functionality in various scenarios.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Revolutionizing Fake Currency Detection: CNN-Based Approach for Indian Rupee Notes

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ratnesh K. Choudhary,
  • Swapnil Mahajan,
  • Pravin Jaiswal,
  • Shweta Gupta,
  • Prachi Borate,
  • Tannu Shahu,
  • Vibhanshu Mandaogade

摘要

Despite a global shift toward digital payments, counterfeit banknotes remain a significant issue due to the continued use of paper currency. In India, the Reserve Bank of India (RBI) faces substantial challenges in identifying counterfeit notes amid evolving counterfeiting techniques. We created a CNN-based model to detect counterfeit Indian rupee bills worth ₹50, ₹100, ₹500, and ₹2000. Trained on a comprehensive dataset of top-notch banknote images, it reached an impressive 98% accuracy in tests and 99% during training. This model operates with increased speed and accuracy for real-time detection compared to conventional methods. Connecting this model to systems of the Reserve Bank of India (RBI) can enhance the efficiency of counterfeit currency detection, leading to savings in time and resources. This novel method provides a contemporary answer that is faster and more accurate than earlier approaches. It has the potential to completely change the RBI's management of counterfeit detection by optimizing operational workflows and the detection process itself if it is integrated with the RBI's present systems. Our future work will concentrate on extending the model's use to additional currencies and enhancing its functionality in various scenarios.