Number identification method based on SVM

A support vector machine and recognition method technology, applied in the field of number plate recognition, can solve the problems of slow classification speed and low recognition rate, and achieve the effect of high recognition accuracy and strong robustness

Active Publication Date: 2016-10-12
ZHEJIANG UNIV OF TECH
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies of manual classification, slow classification speed, and low recognition rate of existing number plate recognition methods, the present invention provides a method that can replace traditional manual clas

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
  • Number identification method based on SVM
  • Number identification method based on SVM
  • Number identification method based on SVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with the accompanying drawings.

[0036] refer to figure 1 , a kind of number plate recognition method based on support vector machine, described recognition method comprises the steps:

[0037] 1) Obtain number plate image I 1 ;

[0038] 2) Carry out color preprocessing to the image, the specific steps are as follows:

[0039] 2.1) Convert the image I 1 Perform color space conversion to obtain image I in HSV color space 2 ;

[0040] 2.2) The image I 2 Perform histogram equalization to obtain image I 3 ;

[0041] 2.3) Convert the image I 3 According to the brightness threshold, the grayscale image I is obtained 4 ;

[0042] 3) For image I 4 Carry out Canny operator edge detection to get the edge image I 5 ;

[0043] 4) For edge image I 5 Carry out the rectangular frame of the digital area, the specific steps are as follows:

[0044] 4.1) By pairing the edge image I 5 Perform contour ex...

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

Provided is a number identification method based on a SVM. The method comprises the following steps of: 1) acquiring a number plate image I1; 2) performing color preprocessing on the image I1 to obtain a grayscale image I4; 3) performing Canny operator edge detection on the image I4 to obtain an edge image I5; 4) performing digital area rectangle framing on the edge image I5 to obtain a contour set k<3> including numbers, recognizing the contour set k<3> including numbers by using a trained number classifier in combination with the original image I1 to obtain specific numbers. The method may substitute for conventional manual classification, increases marathon photograph classification speed, is good adaptive to the flexible material of a number plate and high in recognition rate.

Description

technical field [0001] The invention relates to the technical fields of neural network, computer vision, image processing, pattern recognition, etc., in particular to a method for recognizing number plates in the photographed pictures, which can be used in various competitions, such as marathons and sports meetings. Background technique [0002] As the physical health problems of the Chinese people continue to intensify, national fitness has once again become a hot topic. The vigorous development of urban marathons has gradually replaced the original indoor fitness or non-fitness model with the national fitness model. In recent years, China's marathon events have shown exponential growth, which has also led to the development of related sports equipment, tourism industry and even marathon photo sales. Against such a background, the market has an urgent demand for marathon service platforms, especially for marathon commemorative photos. [0003] Marathon organizers generall...

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): G06T7/00G06K9/62
CPCG06T2207/10004G06F18/2411
Inventor 张永良陈泽坤温从林陆洋周冰
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