Ethiopian Banknote Recognition and Fake Detection Using Support Vector Machine

Abstract

Currency recognition is an important task in numerous automated payment services and used to categorize the banknotes of different nation. The importance of automatic methods for currency recognition has been increasing in the time being because of circulation of fake notes is increased in today's economy. This recognition system contains basic image processing techniques such like image acquisition, image preprocesses, extract features and classification using support vector machine. Basically camera or scanner used for image acquisition. The images of currency processed using a variety of preprocessing techniques and different features of the image extracted using local binary pattern technique, once the features are extracted it is important to recognize the currency using effective classifier called Support vector machine and Finally a prototype able to recognize Ethiopian paper currency with accuracy of 98% shows high performance classification model for paper currency recognition and also verify the validity of given banknotes with average accuracy of 93% rate.