Abstract

Paper currency recognition is one of the important applications of pattern recognition. This application is used to recognize the currency of different countries. Currency recognition system can be used in many places like Hotels, Shops and Automated Teller Machines etc. The currency recognition system should be able to classify this paper currency to the correct class of paper currencies to which it belongs. This paper represents currency recognition system of different countries using different techniques. The paper represents recognition system of different countries like Bangladesh, China, India and recognition system for Euro currency. Different techniques are used to develop these systems like Bangladeshi Currency Recognition System using Negatively Correlated Neural Network, Bangladeshi Currency Recognition System Using Neural Network with Axis Symmetrical Masks and Chinese Currency Recognition System based on BP (Back Propagation) Neural Network Improved by Gene Algorithm, Chinese Currency Recognition by Neural Network, Chinese Currency Recognition based on LBP (Local Binary Pattern). Indian Currency Recognition System based on Heuristic Analysis and Recognition System for Euro using New Recognition Method. This paper represents currency recognition system of different countries and method used to develop these systems.

Highlights

  • The currency recognition system is developed to recognize the currency by applying different techniques and methods on currency note

  • The purpose to use the Gene Algorithm is to get the appropriate result of connection weights and network connection

  • Zhang et al (2003), they had proposed a method to extract the features of RENMINGBI (RMB) currency image

Read more

Summary

Introduction

The currency recognition system is developed to recognize the currency by applying different techniques and methods on currency note. LITERATURE REVIEW Debnath et al (2010), they had used ensemble neural network for currency recognition. The system developed using ENN can identify the currency with noise as well as old currency notes. Due to the slow convergence and indeterminate initial weights for Back Propagation Neural Networks, they had used Gene Algorithm. The purpose to use the Gene Algorithm is to get the appropriate result of connection weights and network connection.

Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call