Kernel density estimation-based license plate character segmentation method

Abstract

The invention relates to a kernel density estimation-based license plate character segmentation method. At present, the conventional methods have the defect that binaryzation cannot be performed well under the extreme condition. The method comprises the following steps of: performing preprocessing of normalization, edge sharpening and noise removal on a license plate image; determining a character area of a license plate; finding a pixel value of which the probability of occurrence is maximum in the current kernel probability density curve and the kernel density half width of the point, and performing image binaryzation by utilizing the two parameters; and extracting a segmentation result of which the score is maximum within the width range to be used as a final character segmentation result. By the method, the distribution of character pixels can be determined accurately; and compared with the common iteration binaryzation method, the method has the advantage that the ambient interference resistant capacity is enhanced greatly.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation, and relates to a character segmentation method based on kernel density estimation. Background technique [0002] The current license plate character segmentation technology is mainly based on the character binarization of the license plate area, and the effective license plate character area is obtained by constraining the prior rules of the license plate character arrangement. This method is disturbed by the environment or the license plate itself. It has a certain anti-interference ability, but it still cannot work normally when the character binarization effect is poor. [0003] In order to solve the problem of poor binarization of license plate characters, existing methods include clustering character foreground points, estimating the width and strokes of license plate characters, and detecting license plate borders. These methods can improve the binarization effect, but t...

AI Technical Summary

Problems solved by technology

[0002] The current license plate character segmentation technology is mainly based on the character binarization of the license plate area, and is constrained by the prior rules of the license plate character arrangement to obtain an effective license plate character area. This method is disturbed by the environment or the license plate itself. It has a certain anti-interference ability, but it still cannot work normally when the character binarization effect is poor

[0003] In order to solve the problem of poor binarization of license plate characters, existing methods include clustering character foreground points, estimating the width and strokes of license plate characters, and detecting license plate borders.

These methods can improve the binarization effect, but in extreme cases, there are still many cases that cannot be binarized well.

Images