A tamper detection method based on character position of vehicle VIN code

A technology for tampering detection and character position, applied in character recognition, character and pattern recognition, instruments, etc., can solve problems such as affecting the accuracy of verification, save manpower and ensure fairness

Pending Publication Date: 2019-02-15
上海眼控科技股份有限公司
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the traditional vehicle annual inspection, the vehicle VIN code tampering detection is mainly through manual inspection. For the case of individual character tampering of the vehicle VIN code, such as the change of the character position, it is difficult for ordinary inspectors to distinguish with the naked eye, which affects the accuracy of the verification.

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
  • A tamper detection method based on character position of vehicle VIN code
  • A tamper detection method based on character position of vehicle VIN code
  • A tamper detection method based on character position of vehicle VIN code

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with the accompanying drawings.

[0043] The present invention is mainly based on a target detection module, a character position detection module and a judgment module.

[0044] Such as figure 2 As shown, the target detection module is composed of a VIN code target detection unit and a character segmentation unit. First, the image is passed into the target detection unit, and the VIN code target detection model is applied on the image to obtain the image of the vehicle VIN code area. Then use the character segmentation model to segment the VIN code into individual characters. The target detection module first detects the vehicle VIN code area, and then performs character segmentation in the vehicle VIN code area. This step-by-step detection method can effectively avoid the influence of false detection caused by the complex situation of the vehicle VIN code area, and improve the accuracy of the vehi...

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 tamper detection method based on character position of vehicle VIN code, which comprises the following steps: obtaining vehicle VIN code image to be detected in vehicle annual inspection and VIN code archiving image in server; obtaining vehicle VIN code image to be detected in vehicle annual inspection. Detecting an area where the VIN code is located, and judging whethera target exists or not; Dividing the VIN code into a single character and judging whether the character matches the answer; constructing A homography matrix by the positions of the first and last characters of the image to be detected and the archived image, and mapping the space of the image to be detected to the space of the archived image. Judging whether the positions of the transformed imagecharacters (the left-right spacing and the upper-lower position of the characters) are consistent with the positions of the image characters archived by the server; If the above judgment exists and isconsistent, recording the flag as 0, otherwise recording the flag as 1, and saving the related picture; If the recording flag is 0, the vehicle VIN code tampering detection is passed, indicating thatthe VIN code has not been tampered with; if the recording flag is 1, the VIN code tampering detection is not passed, indicating that the VIN code has been tampered with. At the same time, according to the position where the flag 1 appears, obtain the reason why the calibration does not pass and the picture of the problem. The invention realizes the automatic verification of the VIN code in the vehicle annual inspection, replaces the existing manual verification mode, saves manpower, speeds up the verification speed, can effectively detect whether the VIN code is tampered with, and ensures theopenness and fairness of the verification work.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence judgment for annual inspection of motor vehicles, in particular to a method for tampering detection based on the character position of a vehicle VIN code. Background technique [0002] With the continuous development of social economy and the continuous improvement of people's living standards, the number of urban motor vehicles has increased rapidly. The workload of the annual inspection of motor vehicles has also increased rapidly. In the traditional vehicle annual inspection, the vehicle VIN code tampering detection is mainly through manual inspection. For the case of individual character tampering of the vehicle VIN code, such as the change of the character position, it is difficult for ordinary inspectors to distinguish with the naked eye, which affects the accuracy of the verification. [0003] How to accurately and quickly verify the VIN code of the vehicle, while avoiding ...

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): G06K9/34G06K9/32
CPCG06V20/62G06V30/153G06V2201/09G06V30/10
Inventor 周康明
Owner 上海眼控科技股份有限公司
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