Preprocessing method and device for VIN (vehicle identification number) image

A vehicle identification code and preprocessing device technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of low accuracy, high cost, time-consuming, etc., achieve good versatility, and reduce manual processing costs Effect

Active Publication Date: 2015-07-15
深圳市道通合盛软件开发有限公司
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a preprocessing method and device for a vehicle identification code image, which overcomes the defects of high cost, time-consuming, and low accuracy in the traditional method of manually adjusting the size of the VIN code box

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
  • Preprocessing method and device for VIN (vehicle identification number) image
  • Preprocessing method and device for VIN (vehicle identification number) image
  • Preprocessing method and device for VIN (vehicle identification number) image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0049] see image 3 , in the second embodiment, in order to further improve the recognition efficiency, the VIN image preprocessing device may further include a noise removal unit 140 , a rotation unit 150 and a non-character cutting unit 160 .

[0050]The noise removal unit 140 is used to remove the small noise in the extracted VIN code area. In this embodiment, the noise removal unit 140 calculates the connected domain in the VIN code area, and removes the area with a smaller connected domain, so as to achieve noise removal. the goal of.

[0051] The rotation unit 150 is used to rotate and adjust the VIN code area to the positive direction. Since the direction of the captured image is not necessarily horizontal, the rotation unit 150 is used to rotate the VIN code area and adjust it to the positive direction for subsequent processing.

[0052] The non-character cutting unit 160 is used to remove non-character image information. In this embodiment, the non-character cutting...

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 provides a preprocessing method and device for a VIN (vehicle identification number) image. The method comprises the following steps: a source image is converted into a single-channel gray image from a multi-channel color image; the image obtained after processing is subjected to open operation and close operation sequentially; the image obtained after processing of the open operation and the close operation is binarized to obtain a back-and-white image; a VIN region is extracted from the back-and-white image; the average value of the VIN region is calculated, whether the average value exceeds a preset threshold value is judged, and if the average value exceeds the preset threshold value, the source image is negated and returned to the first step for re-processing. One good preprocessing scheme for the VIN image is provided by an embodiment of the invention, the VIN region can be positioned accurately under the condition of large image and much background noise, non-character image information of two ends of the VIN can be removed, the method and the device are convenient, fast and accurate, the manual processing cost is reduced greatly, good universality is realized, and the method and the device are applicable to VIN images with black characters on white background and white characters on black background.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for preprocessing an image of a vehicle identification code. Background technique [0002] VIN is the abbreviation of Vehicle Identification Number in English. The VIN code consists of 17 characters, so it is commonly known as the seventeen-digit code. The vehicle identification code contains the information of the manufacturer, production year, model, body type, engine and other equipment of the vehicle. The vehicle identification code has many important uses. For example: service commercial vehicle identification code to identify the engine, transmission and brake system configured by the manufacturer, so as to provide more appropriate service for the vehicle. VINs are used by law enforcement agencies to identify or recover stolen vehicles and vehicle accessories. Likewise, vehicle manufacturers use vehicle identification numbers when they need t...

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): G06K9/00G06K9/54
Inventor 刘洋龚煜郭志强
Owner 深圳市道通合盛软件开发有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap