License plate segmentation and identification method

A license plate and license plate positioning technology, which is applied in the field of identification and identification of target items, can solve problems such as high production costs and complicated procedures, and achieve the effects of maintaining integrity, eliminating noise interference, post-segmentation, and improving recognition accuracy

Active Publication Date: 2020-01-24
珠海全信通科技有限公司
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This character recognition method has higher requirements on hardware, and the programmed programs are more complicated, resulting in higher production costs.

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 segmentation and identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technology of the present invention can calibrate the license plate according to the position information of the license plate, perform grayscale and automatic binarization, eliminate noise according to the contour, perform XY axis projection search and continue to narrow the license plate area, divide the license plate into each recognition character unit for X axis projection, and use Machine learning recognizes character units and finally outputs the license plate number.

[0027] Each step in the flow process of the embodiment of license plate segmentation and recognition method is described in detail below in conjunction with accompanying drawing:

[0028] A preferred embodiment of the method for license plate segmentation and recognition of the present invention, comprises the following steps:

[0029] Step S1: Preset Source Map I org and the position of the license plate, including the upper left point P Left_Top , upper right point P Right_Top , lower lef...

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 segmentation and identification method. The method comprises: calibrating the license plate according to the license plate position information; performing grayscale and automatic binaryzation, eliminating noise according to the contour, performing XY-axis projection searching to continuously reduce the license plate area, segmenting the license plate to each recognition character unit through X-axis projection, learning the recognition character units through a machine, and finally outputting the license plate number, so that the license plate can be quickly recognized, and the cost is relatively low.

Description

【Technical field】 [0001] The invention relates to the determination and recognition technology of target items, in particular to a license plate segmentation and recognition method through license plate position information calibration and machine learning. 【Background technique】 [0002] In order to realize efficient, fast and intelligent supervision and management of road vehicles, people have successively developed and developed various traffic road monitoring systems and management systems by using high technology. Through a series of vehicle detection devices and real-time vehicle monitoring equipment, the Road traffic vehicle data information to realize the automation and intelligence of traffic management. License plate image recognition technology is a key technology in the vehicle detection system and a prerequisite for realizing traffic intelligence and automation. At present, intelligent IC card recognition or barcode recognition technology can be used for licens...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/34G06K9/40G06K9/62
CPCG06V30/153G06V10/30G06V10/267G06V20/625G06F18/241
Inventor 韩子天孙文超
Owner 珠海全信通科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products