License plate automatic detection algorithm

Abstract

The invention relates to a license plate automatic detection algorithm comprising the following steps: collecting a color image of a license plate, and extracting the outer boundary of the license plate to obtain a license plate image; performing channel separation on the license plate image to respectively obtain R, G and B three-channel images; selecting suitable channel images according to the license plates with different colors, and respectively carrying out frame detection, character recognition and character defect detection, bottom film detection and/or two-dimensional code detection; and marking a good license plate or a bad license plate according to a detection result. License plate defects are automatically extracted through a machine vision algorithm; character matching is carried out by training a character hot stamping range threshold value, matching is carried out without using standard characters, and meanwhile, edge completion is carried out on an image needing to be detected to detect large-area character over-stamping/missing stamping; through multi-scale comprehensive detection, the detection stability is ensured, so that the defect judgment accuracy is improved, and the small defect detection capability is enhanced; the license plate detection efficiency and accuracy are improved, and manpower is saved.

Description

technical field [0001] The invention relates to the technical field of visual detection, in particular to an automatic license plate detection algorithm. Background technique [0002] In the process of license plate issuance, stamping the license plate will cause damage to the surface of the license plate and defects of hot stamping characters. These defects are currently mainly checked manually, and there is no fixed standard. Bad card data and good card data are easy to cause misclassification. The existing detection algorithm has poor stability in detecting the same license plate, and the detection error rate is high. The reason for the poor detection stability and relatively single defect types is mainly the detection of large defects, because the license plate detection itself does not require strict standards, and there are many types of license plate detection. Contents of the invention [0003] The technical problem to be solved by the present invention is to prov...

AI Technical Summary

Problems solved by technology

[0002] In the process of license plate issuance, stamping the license plate will cause damage to the surface of the license plate and defects of hot stamping characters. These defects are currently mainly checked manually, and there is no fixed standard. Bad card data and good card data are easy to cause misclassification. The existing detection algorithm has poor stability for the detection of the same license plate, and the detection error rate is high

The reason why the detection stability is poor and the type of defects detected is relatively single is mainly due to the detection of large defects, because the license plate detection itself does not require strict standards, and there are many detection types of license plates

Images