License plate positioning method based on traffic monitoring video

Abstract

The invention discloses a license plate positioning method based on a traffic monitoring video. The license plate positioning method specifically comprises the steps of: 1, converting an original image in the traffic monitoring video, converting the original image into a grey-scale image and converting an original color space into an HSV space; 2, preprocessing the converted image; 3, conducting edge detection on the preprocessed image; 4, adopting a local threshold method, a global threshold method and a dynamic threshold method comprehensively on the basis of edge detection, and dividing the image into black and white color regions according to a relation between pixel values and threshold values so as to realize image binarization; 5, adopting expansion, region filling and corrosion operations in mathematical morphology after image binarization, realizing region merging and further noise elimination; 6, subjecting detected edge images to horizontal projection and vertical projection in sequence, so as to determine up, down, left and right boundaries of a license plate; 7, and conducting license plate positioning by means of a support vector machine after projection confirmation. The license plate positioning method can overcome the problems of background noise, background similar pattern interference, license plate character discontinuity and the like in the prior art.

Description

technical field [0001] The invention belongs to the field of video processing, in particular to a license plate location method based on traffic monitoring video. Background technique [0002] With the development of the economy and the improvement of people's living standards, the number of cars has also increased rapidly, which has brought many challenges to urban traffic. Therefore, automatic license plate recognition and analysis technology based on intelligent image processing theory has gained more and more attention. License plate location is a crucial part of license plate recognition, and its accuracy and recall rate are directly related to the work of subsequent links and even the performance of the entire system. [0003] Common license plate location methods include methods based on image texture features, methods based on transformation, methods based on artificial neural networks, methods based on mathematical morphology, and so on. Methods based on image text...

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: Aiming at the problems existing in the prior art, the present invention provides a method for locating license plates based on traffic monitoring video, which can overcome the problems of background noise and background similar pattern interference, discontinuous license plate characters and the like in the prior art

Images