Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Method of License Plate Tilt Correction Based on Neural Network

A technology of tilt correction and neural network, which is applied in the field of image processing and deep neural network, can solve the problems of difficult to accurately detect edges and large amount of calculation, and achieve the effect of small memory usage, small amount of calculation, and fast speed

Active Publication Date: 2020-09-01
XIAMEN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult to accurately detect the edge when it is complex, the edge is not clear and there is a lot of noise. In addition, this method also has the problem of large amount of calculation.

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 Method of License Plate Tilt Correction Based on Neural Network
  • A Method of License Plate Tilt Correction Based on Neural Network
  • A Method of License Plate Tilt Correction Based on Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The technical solution of the present patent will be described in further detail below in conjunction with specific embodiments.

[0060] see Figure 1-5 , a method for license plate tilt correction based on neural network, comprising the following steps:

[0061] 1. Data production

[0062] The training data set is obtained by normalizing the inclination changes and sizes of the existing license plates at different angles and degrees, and the training data set is divided into 25 categories according to the degree of inclination, so that the size of each picture is 72*32, and Each has a specific label, and a portion of the data is randomly selected as a test set according to a 10:1 ratio.

[0063] 2. Design of tilt correction network

[0064] The tilt correction network adopts three layers, see input layer, hidden layer and output layer image 3 ;

[0065] The tilt correction network is divided into the following eight layers:

[0066] The first layer is the input...

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 method for license plate tilt correction based on neural network, comprising the following steps: 1. data creation; 2. tilt correction network design; 3. training network; 4. using trained network; In the picture of the license plate, the image processing knowledge is used to locate and extract the license plate, and then use the network obtained through training to carry out forward propagation recognition and correction, and finally cut it into one character, and then use another neural network for character recognition. The method of affine transformation based on Hough linear transformation to find edges is different, and it still has a high correction rate in the case of complex, unclear edges and many noises, and the use of trained networks for correction is less computationally expensive and faster. .

Description

technical field [0001] The invention relates to the fields of image processing and deep neural networks, in particular to a method for correcting license plate tilt based on neural networks. Background technique [0002] As cars are used more widely and frequently, traffic problems are becoming more and more serious. How to efficiently and quickly manage vehicles has become a key topic for everyone to study. The license plate as the only sign of a vehicle has become a top priority in research. In the intelligent transportation system, the recognition of the license plate is an important part of the intelligent transportation system, which involves the positioning, cutting, character recognition and other technologies of the license plate. In reality, due to various reasons, the license plates we capture and extract often have various degrees of inclination, so this not only brings troubles to character segmentation, but will eventually affect the accuracy of license plate c...

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): G06K9/32G06N3/02
CPCG06N3/02G06V30/1478G06V20/625
Inventor 周剑扬陈琼
Owner XIAMEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com