code for segmenting the indian paper currency using matlab
Posts: 14,118
Threads: 61
Joined: Oct 2014
Paper currency recognition (PCR) is an important area of pattern recognition. A system for the recognition of paper money is a type of intelligent system that is a very important need of today's automation systems in today's modern world. It has several potential applications, including electronic banking, currency monitoring systems, money exchange machines, etc. This document proposes an automatic system of recognition of currencies in paper for paper money. A method of recognizing paper coins has been introduced. This is based on interesting features and correlation between images. It uses the radial network of radial function for classification. The method uses the case of the Saudi paper currency as a model. The method is quite reasonable in terms of accuracy. The system deals with 110 images, 10 of which are tilted with an angle of less than 15 °. The rest of the coin images are composed of mixed including noisy and normal 50 images each. It uses the fourth series (1984-2007) of currency issued by the Saudi Arabian Monetary Agency (SAMA) as a model currency under consideration. The system produces a recognition accuracy of 95.37%, 91.65% and 87.5%, for normal non-tilted images, noisy tilted images and tilted images, respectively. The overall mean recognition rate for 110-image data is estimated to be 91.51%. The proposed algorithm is fully automatic and does not require human intervention. The proposed technique produces quite satisfactory results in terms of recognition and efficiency.