Unlock instant, AI-driven research and patent intelligence for your innovation.

License plate accurate positioning method and device in free scene

A precise positioning and license plate technology, applied in the field of license plate recognition, can solve the problems of low license plate positioning accuracy, inability to apply license plate positioning, and high distribution requirements.

Pending Publication Date: 2020-12-08
GUANGDONG UNIV OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a method and device for precise positioning of license plates in free scenes, which are used to solve the problem that the existing license plate positioning technology has high requirements on the distribution of boundary points in free scenes, and cannot be applied to license plate positioning in complex backgrounds, resulting in the actual The technical problem of low license plate positioning accuracy

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • License plate accurate positioning method and device in free scene
  • License plate accurate positioning method and device in free scene
  • License plate accurate positioning method and device in free scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] For ease of understanding, see figure 1 , Embodiment 1 of a method for accurately locating a license plate in a free scene provided by the present application, including:

[0068] Step 101: Carry out connected domain analysis on the preset license plate image, and retain the marked connected domain meeting the preset contour conditions, record the boundary points of the connected domain, and obtain the upper boundary point set and the lower boundary point set, and the preset license plate image is the original The license plate image is obtained after preprocessing.

[0069] The preset license plate image is the image obtained after preprocessing the original license plate image. The preprocessing operation may include some grayscale or denoising operations in order to obtain a preset license plate image with higher quality and less noise. If for To ensure the integrity of the license plate, it can also expand the memory area. There are many connected domains obtained...

Embodiment 2

[0079] For ease of understanding, see figure 2 , the present application provides a second embodiment of the precise license plate positioning method in a free scene, including:

[0080] Step 201, expand the area of ​​the original license plate image on the basis of rough positioning to obtain a rough license plate positioning map.

[0081] see Figure 4 , the purpose of area expansion is to avoid dividing the license plate of the main research object out of the boundary by rough positioning, so as to expand as large as possible. In addition to the license plate, the original license plate image also includes a background with inconsistent colors, textures, and edges; and the license plate includes a variety of characters.

[0082] Step 202, performing grayscale processing on the rough license plate location map to obtain a grayscale image of the license plate.

[0083] The grayscale processing is in the RGB model. If R=G=B, the color represents a grayscale color, and the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a license plate accurate positioning method and device in a free scene. The method comprises the steps: carrying out connected domain analysis of a preset license plate image,reserving a marked connected domain meeting a preset contour condition, recording boundary points of the connected domain, and obtaining an upper boundary point set and a lower boundary point set; performing straight line fitting on the upper boundary point set and the lower boundary point set by adopting a preset least square method to obtain an upper boundary line segment and a lower boundary line segment; calculating boundary point coordinates of four corners of an area interception frame according to the upper boundary line segment and the lower boundary line segment; intercepting a license plate area image of the expanded original license plate image through an area interception frame; and performing coordinate fitting on the left and right boundaries of the license plate area image by adopting a preset CNN model to obtain a license plate positioning result. A technical problem that actual license plate positioning accuracy is low due to the fact that an existing license plate positioning technology has high requirements for boundary point distribution in the free scene and cannot be suitable for license plate positioning in a complex background is solved.

Description

technical field [0001] The present application relates to the technical field of license plate recognition, in particular to a method and device for precise positioning of a license plate in a free scene. Background technique [0002] With the development of my country's transportation in recent years, the number of cars is increasing, how to efficiently manage cars has become an urgent problem to be solved. Automatic license plate recognition technology helps people to efficiently identify license plates in pictures or camera images, without manual participation in the process; through automatic license plate recognition technology, we can identify specific vehicles in the camera screen, thereby conveniently completing parking Fee collection, community access management and other operations. [0003] The license plate recognition process can be divided into three stages: license plate location, character segmentation, and character recognition. The license plate location i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/34G06K9/40G06K9/62G06T7/12G06T7/181G06T7/73G06T5/00G06N3/04G06N3/08
CPCG06T7/12G06T7/181G06T7/73G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06V10/267G06V10/30G06V20/625G06N3/045G06F18/241G06T5/70Y02T10/40
Inventor 丁磊赖珍向杨明岳顾国生邓杰航江志豪李亚萍
Owner GUANGDONG UNIV OF TECH