Automatic Indian currency denomination recognition system based on artificial neural network

Abstract

Automatic detection and recognition of Indian currency note has gained a lot of research attention in recent years particularly due to its vast potential applications. In this paper we introduce a new recognition method for Indian currency using computer vision. It is shown that Indian currencies can be classified based on a set of unique non discriminating features such as color, dimension and most importantly the Identification Mark (unique for each denomination) mentioned in RBI guidelines. Firstly the dominant color and the aspect ratio of the note are extracted. After this the segmentation of the portion of the note containing the unique I.D. Mark is done. From these segmented image, feature extraction is done using Fourier Descriptors. As each note has a unique shape as the I.D. Mark, the classification of these shapes is done with the help of Artificial Neural Network. After feature extraction, the denominations are recognized based on the developed algorithm. The success rate of the proposed system is 97% requiring a processing time of 2.52 seconds.

Automatic Recognition and Counterfeit Detection of Ethiopian Paper Currency

“…The texture of the currency is extracted as intrinsic features fur currency recognition, and the class discriminating capability of these features for Indian currency is evaluated. On the other hand, Gogoi et al [9] classify Indian currency based on a set of unique features such as color, dimension and identification mark. Since each banknote has unique shape as identification mark, Fourier descriptor is used to extract the features.…”

“…Some other countries have been attempting to develop systems that recognize their respective currencies Copyright © 2016 MECS I.J. Image, Graphics and Signal Processing, 2016, 2, 28-36 [9,10,12,14,15,18]. To the best of our knowledge, however, there is no research and development work focused on recognition of Ethiopian paper currency which is known as Birr.…”

Currency Recognition Using Image Processing and Minimum Distance Classifier Technique

“…RELATED WORK Automatic Indian Currency Denomination Recognition System based on Artificial Neural Network [1] that Indian currencies can be classified based on a set of unique non discriminating features such as color, dimension and most importantly the Identification Mark (unique for each denomination) mentioned in RBI guidelines. At the beginning the dominant color and the aspect ratio of the note are extracted.…”

“…There are 6 currency notes in India, with each of them looking different. For instance, the size of the paper is different, the same as the color and pattern [1]. People have to detect and recognize different types of currency denomination and that is not an easy job.…”

“…Image Acquisition, Image Preprocessing, Segmentation, Feature Extraction, Recognition [1]. Among these the Segmentation and Recognition is the most important stage and also the most difficult part.…”