Supercharge Your Innovation With Domain-Expert AI Agents!

A license plate recognition method for non-motor vehicles

A non-motor vehicle, license plate recognition technology, applied in neural learning methods, character and pattern recognition, computer parts and other directions, can solve the problems of reduced accuracy of license plate characters, many interfering characters, etc., to enhance accuracy and detection and recognition. effect of speed

Active Publication Date: 2022-05-03
ZHEJIANG GONGSHANG UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] ③ Due to too many interfering characters, the accuracy of the recognized license plate characters (including numbers) is reduced

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 license plate recognition method for non-motor vehicles
  • A license plate recognition method for non-motor vehicles
  • A license plate recognition method for non-motor vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Below in conjunction with accompanying drawing, the present invention will be further described, as figure 1 Shown, the present invention specifically comprises the following steps:

[0026] Step 1: For the obtained non-motor vehicle original license plate image, judge its background color, if it is white, the license plate background color remains unchanged, if it is yellow, respectively convert the license plate background color to white, and call their image histogram Figure, set the pixel mean of background pixels to N 1 , the pixel mean of character pixels is N 2 , where (N 1 >N 2 ), for non-motor vehicle license plates with background colors of other colors, if necessary, the background color can also be changed to white, and the characters and numbers can be changed to black. Here, the background color is white, the characters and numbers are black and Take the non-motor vehicle license plate with yellow background, black characters and numbers as an example....

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 non-motor vehicle license plate recognition method. The invention first uses BP neural network to digitally recognize the numbers in the non-motor vehicle original license plate image, and obtains the numbers in the non-motor vehicle original license plate image after digital recognition. area. Secondly, search and expand the name of the target area to be recognized, take the expanded complete target area as sample input, and construct the Faster R-CNN network. Then object region detection and extraction are performed. Finally, for the extracted non-motor vehicle target area, use BP neural network to recognize characters and numbers. The present invention not only maintains the advantages of deep learning technology in target detection and recognition, effectively enhances the accuracy of the target region detection of non-motor vehicle license plates and the speed of detection and recognition, but also improves the accuracy of BP neural network for non-motor vehicle license plates. The recognition rate of characters and numbers in .

Description

technical field [0001] The invention relates to a method for target detection and recognition, in particular to a method for recognizing non-motor vehicle license plate characters and numbers based on a target region extraction combined with Faster-RCNN and BP neural network. Background technique [0002] The non-motor vehicle license plate is different from the motor vehicle license plate. The format of the motor vehicle license plate is generally a rectangle with a blue background. Five-digit characters (generally composed of letters and numbers), the front, rear, left, and right positions of the license plate except for the license plate number characters have no interference, and the format is relatively uniform. However, the format of non-motor vehicle license plates is generally composed of the district name under the jurisdiction of the city and a series of numbers, and the length of the string of numbers is not equal. The license plate area code of the color is repl...

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 Patents(China)
IPC IPC(8): G06V10/26G06V30/24G06V30/194G06N3/04G06N3/08
CPCG06N3/084G06V30/153G06V10/267G06V20/625G06N3/045
Inventor 吕浩章熙沈伟斌冯吉红潘庆张宸逍马震威王效灵
Owner ZHEJIANG GONGSHANG UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More