Vehicle number recognition method and device

A recognition method and vehicle number technology, applied in the field of image processing, can solve the problems of low character recognition accuracy and achieve the effects of low character recognition accuracy, high recognition rate and anti-distortion

Inactive Publication Date: 2016-02-24
SHANDONG BOANG INFORMATION TECH CO LTD
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of this, the present invention provides a vehicle number recognition method

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
  • Vehicle number recognition method and device
  • Vehicle number recognition method and device
  • Vehicle number recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] An embodiment of the present invention provides a vehicle number identification method.

[0078] Locomotives include various models, such as SS7, SS3, HX3, HX1, DF4, DF5, DF7, etc. Each model is divided into different categories. For example, SS7 type vehicles include SS7, SS7C, and SS7B. There are also many colors of locomotive numbers: red letters on a blue background, white letters on a red background, dark green and white letters, and white letters on a red background. The depth of the red background is also different. The locomotive car number is composed of car number characters and terminal symbols. The invention designs a variety of recognition algorithms for various vehicle types, including the identification of vehicle number characters and terminal symbols, so that it has a higher recognition rate for various types of locomotives.

[0079] The recognition of the vehicle number characters and the recognition of the terminal symbols are mainly carried out by u...

Embodiment 2

[0125] The embodiment of the present invention provides a car number recognition device, such as Figure 5 As shown, the device includes:

[0126] The normalization module 01 is used to normalize each vehicle model sample picture of a plurality of vehicle model sample pictures acquired in advance to obtain a plurality of standard sample pictures;

[0127] The character training module 02 is used to train the neural network according to the car number characters of a plurality of standard sample pictures to obtain the character convolutional neural network structure;

[0128] The terminal training module 03 is used to train the neural network according to the terminal symbols of a plurality of standard sample pictures to obtain the terminal convolutional neural network structure;

[0129] The recognition module 04 is used to respectively use the character convolutional neural network structure and the terminal convolutional neural network structure to recognize the pre-collect...

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 provides a vehicle number recognition method and device. The method comprises the following steps of respectively carrying out normalization on each of a plurality of pre-obtained vehicle model sample pictures to obtain a plurality of standard sample pictures; obtaining a character convolutional neural network structure according to a vehicle number character training neural network in the standard sample pictures; obtaining an end position convolutional neural network structure according to an end position character training neural network in the standard sample pictures; and respectively utilizing the character convolutional neural network structure and the end position convolutional neural network structure to recognize the pre-collected vehicle model pictures to obtain a vehicle number. The device comprises a normalization module, a character training module, an end position training module and a recognition module. According to the vehicle number recognition method and device, the vehicle number is obtained by utilizing the trained character convolutional neural network structure and the end position convolutional neural network structure, so that the accuracy rate for recognition is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a vehicle number recognition method and device. Background technique [0002] Vehicle number recognition technology is an intelligent traffic management system based on digital image processing and character recognition. It is an important link in the vehicle detection system. Toll collection system, urban traffic vehicle management, non-stop payment, stolen vehicle inquiry, parking lot management, vehicle access control for special departments, etc. Applied in the railway transportation management system, the car number recognition technology realizes the automatic identification of train number and car number, provides real-time basic information such as train number and car number for railway transportation management, improves the operation efficiency of marshalling stations, and reduces the labor intensity of operators. Combined with the cargo ticket system, it can...

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
IPC IPC(8): G06K9/34G06K9/62
CPCG06V30/153G06V20/625G06F18/214
Inventor 孙希伟
Owner SHANDONG BOANG INFORMATION TECH CO LTD
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