License plate recognition method based on sequence learning

A license plate recognition and sequence technology, applied in the field of license plate recognition based on sequence learning, can solve the problems of license plate recognition methods such as missed detection and multiple detection, complicated and different heuristic rule design, and achieve good sequence conversion results, flexible recognition problems, and stress-reducing effect

Active Publication Date: 2019-09-27
ZHEJIANG UNIV OF TECH
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] To sum up, the current license plate recognition methods are facing the following problems: 1) A variety of license plate formats is one of the main challenges for related research; 2) There are missing and multiple detections in the license plate recognition method based on character detection; 3) Although the artificial heuristic method is efficient and accurate, the design of the heuristic rules is complicated, and different strategies need to be adopted for different license plates

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 recognition method based on sequence learning
  • License plate recognition method based on sequence learning
  • License plate recognition method based on sequence learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The schematic diagram of the present invention is as figure 1 As shown, the specific implementation of the license plate recognition method based on the re-recognition strategy of the present invention will be described in detail below in conjunction with the embodiments.

[0033] Step 1: First prepare the license plate character detection data set, and mark the position rectangle box R and category label C of each license plate character on each license plate, C∈D, D is the character index table; then use the training data set based on the prepared Deep Convolutional Neural Network Model M for License Plate Character Detection C ; In this example, choose the official YOLOv3 neural network structure training to get the model M C ;

[0034] Step 2: Train the Sequence-to-Sequence model M for sequence conversion S , the specific steps are:

[0035] Step 2.1: Input the image I to be trained into the license plate character detection network M C , encoding to obtain the...

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 license plate recognition method based on sequence learning, and belongs to the technical field of intelligent traffic. A license plate image is changed into a sequence composed of candidate characters through a deep neural network used for character detection and recognition, then the sequence is input into a sequence conversion model obtained through training, a new character index sequence is obtained, and finally original candidate characters are recombined according to indexes to obtain a license plate recognition result. According to the license plate recognition method based on sequence learning obtained through the technology, a machine autonomously learns license plate character selection, rejection and permutation combination rules, the pressure of manually designing heuristic rules is reduced, learning experience is achieved with the help of a large number of data samples, and a sequence model can be more flexible in the aspect of the recognition problem of multi-standard license plates. Compared with a traditional sequence processing method, such as hidden Markov, the method has the advantages that the connection of the sequence elements can be found in long-time dependence, and a better sequence conversion result is obtained.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, and specifically designs a license plate recognition method based on sequence learning. Background technique [0002] Automatic license plate recognition is a technology that combines multiple tasks such as image processing, machine learning and pattern recognition. After decades of development, license plate recognition technology has entered the stage of large-scale commercial use, and its application fields include access control in public places, traffic checkpoint monitoring, and traffic intersection monitoring. [0003] With the development of intelligent transportation technology, the commercial license plate recognition system has applied deep learning to the solution of practical problems, and announced that its license plate recognition rate is as high as 99%. Literature (Y.Zhao, Z.Yu, and X.Li, "Evaluationmethodology for license plate recognition systems and experim...

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): G06K9/62G06K9/32
CPCG06V20/63G06V20/625G06V30/10G06F18/28G06F18/214
Inventor 高飞蔡益超葛一粟卢书芳程振波
Owner ZHEJIANG UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap