Color processing method for identification of areas within an image corresponding to monetary banknotes

Abstract

A color processing method for identification of areas within an image corresponding to monetary banknotes includes dividing the image into a plurality of sections; extracting color histogram data for each section; assigning a color vector for each section according to the color histogram data for the section; comparing the color vector for each section to a color lookup table to determine a probability of the section corresponding to monetary banknotes; and selecting probable sections having the probability exceeding a first predetermined threshold.

Description

technical field [0001] The present invention relates to image processing technology, in particular to a color processing method for identifying multiple regions in an image corresponding to monetary banknote. Background technique [0002] The automatic identification and verification of the well-known currency banknotes is a practical application in the retail transaction market and business environment, and the well-known electronic verification mechanisms of various currency banknote types help to improve the security of financial transactions, and can also avoid Merchants who sell goods receive counterfeit currency banknotes. In addition, currency banknote detectors currently available on the market generally first scan the image of a sample currency banknote, wherein the validity of the sample currency banknote is determined through a series of tests , and the tests used by it may include tests for well-known currency banknote sections or landmarks, holograms, reflective...

AI Technical Summary

Problems solved by technology

[0003] However, with the rapid advancement and availability of printing technology, the circulation of counterfeit or illegally reproduced currency banknotes has become more and more serious, and counterfeiters now have access to highly sophisticated equipment and methods to reproduce some Well-known currency banknotes, and can produce replicas that are indistinguishable from fakes by human vision and touch

[0004] In addition to the increasing difficulty in identifying legitimate currency notes, it is also desirable to be able to detect sample currency from images that are larger than the sample currency being scanned, so that any common scanner can be used Scanning a banknote (or multiple banknotes), it is also possible to scan and identify multiple banknotes at a time, however, doing so will cause more problems when the banknote is placed on an arbitrary background and has displacement and rotation variability, while Many current currency banknote detectors can generally only scan one banknote at a time, and only scan the area closest to the banknote, so as to omit the consideration of the background, rotation and alignment of the banknote

[0005] In addition, when financial notes (monetary banknotes) are scanned embedded in a complex image background, it becomes very difficult to distinguish the actual financial notes from the background of the image. At the same time, the image The background can also provide additional noise and / or patterns that complicate the inspection process and can lead to unexpected results and misjudgments

Images