License plate location algorithm using horizontal gradient and saturation

Abstract

The invention discloses a license plate location algorithm using the horizontal gradient and saturation. The invention relates to the field of license plate location technology. In the prior art, the accuracy of license plate location is often not high under the condition that the image has a complicated background. The main steps of the invention include: firstly, performing coarse locating respectively by using horizontal gradient and image saturation features, and combining the two groups of coarsely-located license plate candidate regions; then precisely locating each of the coarsely-located license plate candidate regions; and finally, performing the fake license plate removal operation on the several license plate candidate regions obtained by the precise location, and obtaining a real license plate region. The algorithm of the invention can effectively avoid the omitted and erroneous locating caused by the use of a single feature by combining the gradient and saturation features for the license plate location, and meanwhile, can effectively reduce license plate locating errors by combining of the coarse locating and the precise locating. The algorithm of the invention can quickly locate the license plate from images with different complicated backgrounds and has high locating accuracy.

Description

technical field [0001] The invention relates to the technical field of license plate positioning, in particular to a license plate positioning algorithm using horizontal gradient and saturation. Background technique [0002] License plate location refers to determining the position of the license plate in the image based on the features of the license plate. The quality of the positioning result will directly affect the subsequent character segmentation and recognition results. As the core step in the whole system, many researchers at home and abroad have conducted in-depth research on the license plate location algorithm and proposed many location methods. Each method has its own advantages and disadvantages. Generally speaking, these methods are mainly based on some special features of the license plate itself (such as: grayscale texture features, geometric shape features, etc.) to locate. Commonly used positioning methods include the following categories: [0003] (1) L...

AI Technical Summary

Problems solved by technology

[0016] In view of the above-mentioned prior art, the purpose of the present invention is to provide a license plate location algorithm utilizing horizontal gradient and saturation, which solves the problem of lack of saturation-based compensation rough positioning and the inability to filter out the vertical projection value sequence in the prior art under complicated circumstances. Technical problems such as low positioning accuracy caused by the vertical projection value of medium noise or the vertical projection value of similar license plate image

Images