Currency detection using similarity indices method

Abstract

The determination of the currency denomination is an issue in paper currency recognition system. This paper proposes a robust method to recognize the paper currency using the pattern matching. In the proposed algorithm a similarity measure is used to classify the currency based on the similarity of the extracted features. To evaluate the performance of the proposed method experiments were conducted over 200 of currencies of different denominations. On performing the experiment the proposed method gives 97% accuracy.

A Review on Indian Currency Recognition

“…Vishnu R, Bini Omman [1] proposed a method where the system compare the features which are extracted from the given input note by computing the similarity measure between the features of the input note and the template image of the particular feature. Jaccard Similarity Indices is used for calculating similarity measured.…”

“…To get currency images in exact size enable auto cropping at the time of scanning the currency. By scanning the currency database are prepared, so there will be a less noise in images so few steps are required for preprocessing [1,2].…”

“…ROI dimensions of all features are taken and the portion of the note is cropped from images that comes inside the ROI and saved as separate image [1,2,3,4].…”

“…In such situations for the classification of the bank notes the machine will use the currency recognizer. [1] Currency has two types of features internal and external features. External features include physical aspects of the currency like width and size.…”

“…For currencies of each denomination there is a specific color and size followed by Reserve bank of India. [1,2] It is a very simple for human to identify the denomination of currency note because our brain is extremely skillful in determining new matters and discovering them later without much trouble. But this currency recognition task turns to very challenging in computer vision, in case of when currencies becomes damaged, old, and faded due to wear and tear.…”