Detection method of license plate and device thereof

A technology of license plate detection and license plate area, which is applied in the field of image processing, can solve the problems of embedded devices that are difficult to meet the requirements of calculation speed, large amount of calculation, and high angle requirements, and achieve the effect of large-angle detection

Active Publication Date: 2014-04-23
SHENZHEN JIESHUN SCI & TECH IND
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has a high detection rate but a slow speed. Carrying out Haar detection on the whole image can accurately detect the license plate, but it has a large amount of computation. If it is applied to embedded devices, the computing speed of embedded devices is difficult to meet the requirements.
In addition, Haar detection has high requirements on the angle. If the angle of the license plate exceeds 30 degrees, there will be some missed detection.

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
  • Detection method of license plate and device thereof
  • Detection method of license plate and device thereof
  • Detection method of license plate and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] figure 1 The implementation flow of a license plate detection method provided by the first embodiment of the present invention is shown, and the details are as follows:

[0041] S101, use the HOG model to perform multi-scale detection on the image, and extract the frame area detected by the HOG model.

[0042] Use the HOG (Histogram of oriented gradients) gradient direction histogram feature to characterize each positive and negative sample to form a HOG feature vector. HOG describes the local gradient magnitude and direction features of the image, and normalizes the feature vector of the block based on the gradient feature. HOG allows blocks to overlap each other, so it is not sensitive to illumination changes and small offsets, and can effectively describe edge features. The license plate detection effect is good for large angles. Afterwards, the HOG model is established through the formed HOG feature vector, and the multi-scale detection is carried out through the...

Embodiment 2

[0051] figure 2 The implementation flow of a license plate detection method provided by the second embodiment of the present invention is shown, and the details are as follows:

[0052] S201. Establish a HOG model according to the collected positive and negative samples.

[0053] A large number of license plate pictures and non-license plate pictures are selected as positive and negative samples of the training set. The selection process can be manually selected, and then each positive and negative sample is characterized by using HOG features to form a feature vector and establish HOG Model.

[0054] .

[0055] S202, converting the image, converting the image into a grayscale image; scaling the image.

[0056] First, convert the image captured by the camera into a grayscale image. By converting the image into a grayscale image, the amount of calculation for image processing can be reduced; the converted image is scaled, and the specific implementation In the process, the w...

Embodiment 3

[0069] image 3 A structural diagram of a license plate detection device provided by the third embodiment of the present invention is shown, and for convenience of description, only parts related to the embodiment of the present invention are shown.

[0070] The frame area extraction unit 31 is configured to use the HOG model to perform multi-scale detection on the image, and extract the frame area detected by the HOG model.

[0071] The box area extraction unit is used to characterize each positive and negative sample using HOG features to form HOG feature vectors. HOG describes the local gradient magnitude and direction features of the image, and normalizes the feature vector of the block based on the gradient feature. HOG allows blocks to overlap each other, so it is not sensitive to illumination changes and small offsets, and can effectively describe edge features. The license plate detection effect is good for large angles. Afterwards, the HOG model is established thro...

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 present invention is applicable to the field of image processing, and provides a detection method of license plate and a device thereof, the method includes the following steps of: performing multi-scale detection for the images by using a HOG model and extracting a pane area via the HOG model detection; calculating an edge of the image and an integrogram image of the image after edge computation to gain the edge integrogram iamge of the image; gaining the pane area via the HOG model detection on the edge integrogram iamge, calculating an edge density of the pane area via the HOG model detection, and extracting the edge density greater than or equal to the pane of the threshold value; via a Haar model, detecting the edge density greater than or equal to the pane of the threshold value to gain the exact license plate area. The present invention by the HOG features detects the images, and then performs the detection the edge and the edge density, finally the license plate area is detected by the haar model.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a license plate detection method and device. Background technique [0002] License plate recognition has been widely used in entrances and exits of parking lots, entrances and exits of commercial buildings, etc. License plate recognition is generally divided into three steps: license plate detection, character segmentation and recognition, and license plate voting. License plate detection, that is, detecting the license plate from the video, and ticket detection is a very important step in license plate recognition, and it is also the most time-consuming step. License plate detection is to detect the position of the license plate in the vehicle image. Since the license plate recognition equipment is generally used outdoors, the imaging conditions of the license plate and the background are uncontrollable. Lighting, complex backgrounds, camera installation angles and distances ha...

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): G06K9/00G06K9/66G06T7/00
Inventor 唐健李昕李锐
Owner SHENZHEN JIESHUN SCI & TECH IND
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