Supercharge Your Innovation With Domain-Expert AI Agents!

License plate detection method and system based on convolutional neural network

A convolutional neural network and license plate detection technology, which is applied in the field of license plate detection methods and systems based on convolutional neural networks, and can solve problems such as the failure of final acquisition of the license plate area and the increase of operation time.

Inactive Publication Date: 2018-12-28
SHANGHAI JIAO TONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the acquisition of the final candidate area of ​​the license plate in this technology is completely dependent on the rough selection area of ​​the license plate obtained by the Adaboost license plate detector based on Haar features. If the rough selection of the license plate area does not include the license plate area, the final acquisition of the license plate area must fail; At the same time, this roundabout detection method requires two steps to complete the detection of the license plate area, which increases the calculation time

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 detection method and system based on convolutional neural network
  • License plate detection method and system based on convolutional neural network
  • License plate detection method and system based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Such as figure 1 As shown, this embodiment includes the following steps:

[0032] Step 1, image preprocessing:

[0033] Step 1.1: Take photos of vehicles (including backgrounds) under different weather conditions and different scenes, segment license plate and non-license plate pictures from the photos, and label them (license plate or non-license plate), and get 5000 license plate pictures, non-license plate pictures 5000 pictures;

[0034] Step 1.2: Convert the above 10,000 color images into grayscale images;

[0035] Step 1.3: Normalize the size of the grayscale image in step 1.2 to 32*32, and each image gets 32*3 two pixel values;

[0036] Step 1.4: Arrange the pixels into a 32*32 matrix according to the spatial position, and save it in the training sample set. Each 32*32 matrix represents a picture, and each sample includes a picture matrix and a corresponding label;

[0037] Step 2, Construct Convolutional Neural Network CNN:

[0038] The CNN adopted in this ...

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 belongs to the field of image processing and artificial intelligence and relates to a convolutional neural network-based license plate detection method and system. An image library with a label is established as a sample set used to train the convolutional neural network; the trained convolutional neural network is used to process an image to be detected; according to an output vector of the convolutional neural network, whether the image is a license plate image and a most matching license plate are judged. The convolutional neural network-based license plate detection method and system has the advantages that recognition and detection precision can be improved and feasibility and robustness are better.

Description

technical field [0001] The present invention relates to a technology in the field of image processing and artificial intelligence, in particular to a license plate detection method and system based on a convolutional neural network. Background technique [0002] The intelligent traffic violation monitoring and management system (commonly known as electronic eyes) monitors and manages motor vehicle violations such as running red lights, going the wrong way, speeding, crossing the line, and illegally parking. The system obtains pictures of illegal vehicles through monitoring, and then further extracts vehicle information from the pictures, such as: license plate, model, car logo, etc. Based on this application background, the present invention proposes a license plate detection method based on a convolutional neural network, which is a method based on machine learning. [0003] Machine learning is an important discipline in the field of artificial intelligence. Early machine...

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): G06K9/00G06N3/08
Inventor 李建勋刘巧巧
Owner SHANGHAI JIAO TONG UNIV
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

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com