Banknote splicing seam or crease recognition method and system

Abstract

The invention discloses a banknote splicing seam or crease recognition method and system. A method of combination of a differential edge detection operator and a proportional coefficient method for binarization is adopted so that weak splicing seam signals can be extracted and recognized. Besides, special processing and limiting modes that the number and length of splicing seams or creases to be recognized are set and angle range of the splicing seams or creases to be recognized on a banknote is limited are applied, an image vertical and horizontal projection method is adopted when a polar angle theta is close to a horizontal or vertical angle, and a Hough transformer detection algorithm is adopted when the polar angle theta largely deviates from the horizontal or vertical angle so that algorithm time is greatly shortened, the objective of rapid detection of the splicing seams or creases can be achieved, algorithm real-time performance can be greatly solved and recognition performance can be guaranteed, the recognition effect of relatively precise splicing seams or creases is great and universality is high. The banknote splicing seam or crease recognition method and system can be widely applied to the field of banknote recognition.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and system for identifying seams or creases of banknotes. Background technique [0002] Assembled currency is a kind of counterfeit currency with a high degree of simulation. Criminals cut a real banknote into several pieces, each with the anti-counterfeiting features of the real currency, and then glue and splice them with fake banknotes to form several complete fake banknotes. banknotes, making the amount of counterfeit money doubled several times. [0003] The simulation of spliced ​​banknotes is so high that it can fool the recognition of banknote counters, sorting machines, and ATM machines. At present, there are only 1 / 8 or less of the counterfeit part of some mosaic coins. The 1 / 8 of the counterfeit part uses the existing multi-spectral images such as infrared reflection map, ultraviolet reflection map, visible light map and magnetic signal to co...

AI Technical Summary

Problems solved by technology

At present, the seam identification effect of banknotes is not very ideal, mainly because the current production of counterfeit money is very fine, and the seam is not obvious. Directly identifying the seam or crease of the banknote will miss detection, and the seam is in the real currency. It is difficult to find the position on the network if it is not fixed, or the method adopted has not been optimized for algorithm speed and cannot adapt to real-time operation and detection under the corresponding embedded hardware platform

[0005] A crease is a defect on a banknote, which is caused by repeated folding during its circulation. If it continues to circulate, the banknote may be torn, so this type of banknote should also be identified At present, financial machines rarely recognize banknotes with this defect type, so it is necessary to increase the crease recognition function of banknotes

Images