A hybrid fake banknote detection model using OCR, face recognition and hough features

Abstract

Currency duplication is now a common occurrence due to the advancement of printing and scanning technology. Many note detection systems are present in banks but they are very costly. In this paper, we are proposing an accurate and consistent technique for fake banknote recognition. We are developing an image processing algorithm which will extract different currency features and compare it with features of original note image. As an output, information about whether the note image is original or duplicate is given. Three main features of paper currencies has been implemented which are micro-printing, water-mark, and ultraviolet lines using OCR (Optical Character recognition), Face Recognition and Canny Edge & Hough transformation algorithm of Matlab. We apply these techniques in order to find an algorithm which will easily be applicable and will be efficient in terms of cost, reliability and accuracy. Along with 1000taka note has been tested for checking authenticity hence making our techniques more appropriate for users.