Banknote crack detection method, device and equipment and readable medium

Abstract

The embodiment of the invention discloses a banknote crack detection method, device and equipment and a readable medium, and the method comprises the steps: obtaining a transmission image of a to-be-detected banknote as a target to-be-detected image, and carrying out the smoothing of the target to-be-detected image, and obtaining a target smooth image; performing binarization processing on the target smooth image to obtain a target binarized image, and determining connected domain information of the target binarized image; and determining whether there is a crack in the banknote to be detected according to the connected domain information. According to the invention, the paper money crack detection efficiency and accuracy are improved.

Description

technical field [0001] The invention relates to the technical field of image processing and recognition, in particular to a banknote crack detection method, device, equipment and readable medium. Background technique [0002] The wide application of cash self-service equipment puts forward higher and higher requirements for banknote processing technology, especially the detection of the circulation of banknotes. As one of the types of non-compliant banknotes that is likely to cause banknotes to be jammed, the detection of torn banknotes is also an important part of the detection of non-negotiable banknotes, which requires equipment such as cash self-service equipment to detect the tearing Banknotes are identified to further judge whether to accept or judge the banknotes as non-negotiable banknotes and input them into the reject box. [0003] In the prior art, for the detection of torn banknotes, it is usually to detect whether there is a connected domain whose edge pixel gr...

AI Technical Summary

Problems solved by technology

[0004] The defect of the above method is that to make the existing crack region show a connected domain with a grayscale close to 255, the optical environment for transmission image acquisition is very demanding, and at the same time, judging whether the pixel value of the edge of the banknote satisfies the grayscale condition will cause There are tears inside banknotes that are missed, which makes the detection of banknote cracks difficult and less accurate

Images