Author: Ch. Ratna Jyothi , Dr. Y.K. SundaraKrishna , Dr.V.SrinivasaRao
Abstract:Monetary transactions are an integral part of our day to day activities, so currency authentication has become one of the active research areas of late, and it shows a vast potential for different applications. In this paper, we introduce a system to verify the authentication of banknotes’ bench mark dataset using computer vision.We considered 1372 samples of various bank notes in our work. The technology of currency authentication aims to search and extract potential features of paper currency for efficient classification. Features were extracted from images that were taken from genuine and forged banknote-like specimens. They are classified using Artificial Neural network. The variance of Wavelet Transformed image (continuous), skewness of Wavelet Transformed image (continuous), curtosis of Wavelet Transformed image (continuous), entropy of image (continuous) features are extracted from images for accurate classification. Our proposed system authenticates bank notes with zero percent misclassification.
Keywords: Currency Recognition, Artificial Neural Network, Classification, Wavelets
Full Issue
| View or download the full issue | PDF 29-38 |