Deep Learning Based Indian Currency Coin Recognition

Abstract

Automatic coin recognition and identification systemplays vital role in vending machine, slot machine and in several banking related equipment's. Most of the existing coin recognitions systems are based on physical parameters of the coins whereas image processing methodologies relies on extraction of color, shape and edge features. For recognition and detection of Indian coin we have proposed Deep Learning approach in this paper. Pretrained convolutional neural network i.e. AlexNet is trained by using the features such as textures, colors and shape. The model is trained on more than 1600 images and can classify images into four object categories like one, two, five and ten rupees coins. The trained model is tested on various standard and own recorded datasets consist of rotational, translated and shifted images. The parameters used to calibrate the performance system are recognition accuracy and response time. Obtained results shown the outperformance of proposed methodology over conventional systems.