Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
LICENSE PLATE RECOGNITION METHOD AND APPARATUS, AND COMPUTER-READABLE STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2024/011888
Kind Code:
A1
Abstract:
Provided in the embodiments of the present invention are a license plate recognition method and apparatus, and a computer-readable storage medium. The method comprises: acquiring a license plate image to be recognized; by means of a object detection model, performing character recognition on the license plate image to determine respective character-related information of a plurality of characters recognized from the license plate image; determining abnormal characters by screening abnormal classes and abnormal areas of different classes of characters, and removing the abnormal characters from amongst the plurality of characters to determine candidate license plate characters; according to position information of the candidate license plate characters, performing linear fitting to determine an arrangement layer where each candidate character is located; according to the numerical order of preset arrangement layers and the position information of the candidate license plate characters, successively splicing the candidate license plate characters in different arrangement layers to determine a license plate number corresponding to the license plate image. In the above solution, performing anomaly screening on the plurality of recognized characters to remove the abnormal characters can raise the accuracy of license plate number recognition.

Inventors:
XIA TAO (CN)
LIU YANG (CN)
Application Number:
PCT/CN2023/073713
Publication Date:
January 18, 2024
Filing Date:
January 29, 2023
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BEIJING JINGDONG QIANSHI TECH CO LTD (CN)
International Classes:
G06V20/62
Foreign References:
CN115147829A2022-10-04
CN114241432A2022-03-25
CN111914845A2020-11-10
Attorney, Agent or Firm:
CHINA PAT INTELLECTUAL PROPERTY OFFICE (CN)
Download PDF: