Identification method of mobile number plate based on three-channel parallel artificial nerve network

An artificial neural network and neural network technology, which is applied in the field of target license plate recognition for moving vehicles, can solve the problems of long training period of BP network, contradiction between accuracy and class diffusion, slow clustering convergence, etc., and achieve the goal of overcoming accuracy and The effect of class diffusion contradiction, overcoming long training period, and system stability

Inactive Publication Date: 2007-12-26
ANHUI VOCATION TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

From the perspective of specific applications, there are only related applications in BP network technology at present, but BP network has long training period, slow clustering convergence, poor adaptability, and extreme value problems may occur
Regarding the ART network technology, no practical application has been found in number plate recognition. At the same time, the existing ART network has the problem of contradiction between accuracy and class diffusion.

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
  • Identification method of mobile number plate based on three-channel parallel artificial nerve network
  • Identification method of mobile number plate based on three-channel parallel artificial nerve network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] A preferred implementation example of the present invention is: referring to Fig. 1, present embodiment is to adopt the mobile car number plate identification method based on three-way parallel artificial neural network, and a number plate example " Anhui A81770 " is identified; Step is:

[0028] 1) Collection of license plate video images:

[0029] For the video image, the preset virtual coil motion video trigger mode is used to automatically trigger the video capture, and the character segmentation of the video capture signal is used as the input signal of the neural network.

[0030] The automatic triggering of the motion video trigger mode is specifically that when a moving vehicle enters the preset virtual detection coil of the screen camera screen, the image will change. The system uses the vehicle license plate graphic template to quickly scan the screen. When the system automatically marks, when the high-speed scanning of the full screen is completed, the multip...

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 relates to a floating number plates discriminating method, which is based on the three-road parallel manmade nerve-net. The identify steps are that adopting the video burst mode to catch the video automatically for the collection of video pictures of the moving vehicle, character cutting the part of pictures of the number plates and then being the input signal of the nerve-net; said nerve-net adopts three standard self-adapt vibrate net each of which has its own work, the three nets are the Chinese characters identify net, the English characters identify net and the data identify net, all of which identify the inputted vector signals at one time, and outputs the most similar sort unity respectively, through controlling the property of the Territory value and the identify accurately according to the number plates and filter, at last add a color property of number plates as the output of the discriminating results. Adopting the method of the invention can identify the number plates of vehicle fast and accurately under the largest driving speed of the vehicles.

Description

Technical field: [0001] The invention relates to a number plate recognition method, more specifically to a method for recognizing a target number plate for a running vehicle. Background technique: [0002] As the object to be managed and controlled, the identity of the moving car must be confirmed. At present, various intelligent transportation application systems based on video recognition of automobile license plates mainly include: automatic identification system for running red lights at intersections, on-site penalty system for vehicle speeding, vehicle identification system at checkpoints, automatic toll payment system for vehicles, automatic management system for parking lots, mobile electronic police system, etc., as the key sensor device of the above-mentioned system, the automatic license plate recognition system must have the characteristics of fast, accurate and easy to obtain, so as to achieve the practical purpose. [0003] At present, there are mainly three m...

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): G08G1/017
Inventor 金庆江刘宗田徐秋红
Owner ANHUI VOCATION 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