Abstract:
Fake currency is a major crime in Sri Lanka. Due to the advances in printing and scanning
technology, it is much difficult to identify a fake currency. This research focuses to verify the
Sri Lankan currency notes via image processing techniques. In the initial stage of this study,
Sri Lankan currency notes are scanned and pre-processed to remove the background and noises.
In the next step, the currency notes are binarized and then segmented. We have extracted the
security thread, blind recognition lines, and raised print marks features through image
processing algorithms. In the evaluation step, the quantity of obtained features and actual
features are compared. Based on the comparison results, we have found that number of lines in
raised printed in each denomination currency note (500, 1000 and 5000) are same, size of all
the circles in the blind recognition feature in each denomination of currency note has
approximately same size, and width of the rectangle in security thread in currency note is same
but it differs for each denomination. In conclusion, the proposed work is able to identify the Sri
Lankan currency notes by comparing the actual features with image processing features
