Coin detection and recognition using neural networks

Abstract

Coin identification and recognition and is important to enhance the extended operation of Vending machines, Pay phone system and coin counting machines. Coin recognition is a difficult task in machine intelligence and computer vision problems because of its various rotations and widely changed patterns. Therefore, an efficient algorithm is designed to be robust and invariant to rotation, translation and scaling. The objective of this work is to find whether the object is coin or not if so denomination of the coin is found. The Fourier approximation of the coin image is used to reduce the variations on surface of coin such as light reflection effect. Then coins can be distinguished by feeding those features into a multi-layered BP neural network.