The automatic detection and recognition of the Indian currency has gained much attention from research in recent years, particularly due to its huge potential applications. It is shown that Indian coins can be classified according to a set of unique non-discriminatory characteristics, such as colour, dimension and, most importantly, the Identification Mark (unique for each denomination) mentioned in the RBI guidelines. First, the dominant colour and the aspect ratio of the note are extracted. After this, the segmentation of the part of the note that contains the only I.D. Mark is done. From this segmented image, the extraction of characteristics is done using Fourier descriptors. As each note has a unique shape like I.D. Mark, the classification of these forms is done with the help of Artificial Neural Network. After the extraction of characteristics, the denominations are recognized according to the developed algorithm. The success rate of the proposed system is 97%, which requires a processing time of 2.52 seconds.
India is a developing country, the production and printing of counterfeit bills of Rs.100, 500 and 1000 are a degrading economic growth of our country. In recent years, due to technological advances in color printing, duplication and scanning, counterfeiting problems enter the scene. In this article, the recognition of paper money with the help of digital image processing techniques is described. About eight characteristics of Indian paper money are selected for the detection of counterfeit notes. Identification marks, optical variable link, see through the currency color code and decide the currency recognition. The security threads, the watermark, the latent image and the characteristics of micro letters are used for currency verification. The extraction of features is done in the image of the coin and compared with the characteristics of the genuine coin. The currency will be verified through the use of image processing techniques. The approach consists of a series of components that include image processing, edge detection, image segmentation and feature extraction, and image comparison. The desired results should be verified with the MATLAB software.