Detecting method and device of vehicle logo

A car logo detection and car logo technology, which is applied to instruments, character and pattern recognition, computer components, etc., can solve the problem of low accuracy of car logos and achieve the effect of improving accuracy

Inactive Publication Date: 2013-05-08
信帧机器人技术(北京)有限公司
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the relatively low accuracy of vehicle logo detection in the related art, the present invention provides a vehicle logo detection method and device to at least solve this problem

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
  • Detecting method and device of vehicle logo
  • Detecting method and device of vehicle logo
  • Detecting method and device of vehicle logo

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] This preferred embodiment provides a method for segmenting and locating vehicle logos based on morphology, the method comprising the following steps:

[0040] Step S2: On the grayscale image, perform morphological edge detection, and then use the area with relatively high edge density as a candidate license plate area;

[0041] Step S4: Perform license plate preprocessing on the area identified as a license plate, and then use the license plate information to roughly locate the vehicle logo area, including license plate positioning, rough positioning of the vehicle logo area, binarization, horizontal correction, and vertical correction.

[0042] Step S6: Use morphological and watershed features to detect vehicle logos in the rough-positioned vehicle logo area with background, and realize automatic positioning and segmentation of vehicle logos.

[0043] As another preferred embodiment, the vehicle logo preprocessing method also includes: using the otsu binarization algorit...

Embodiment 3

[0048] This preferred embodiment provides an effective method for segmenting and locating the vehicle logo above the license plate. Firstly, the approximate area of ​​the vehicle logo is identified according to the license plate positioning information stage, and then in the fine positioning stage, the segmentation process is carried out according to the characteristics of the vehicle logo respectively, and the final segmentation results.

[0049] The method includes steps S302 to S306 as follows.

[0050] Step S302: Coarse positioning of the vehicle logo.

[0051] In this step, edge detection or machine learning algorithms are used to locate the license plate of the input image, and then roughly locate the information area of ​​the vehicle logo according to the license plate positioning information.

[0052] Step S304: preprocessing of the rough positioning area of ​​the vehicle logo: performing horizontal correction on the rough positioning area of ​​the vehicle logo using ...

Embodiment 4

[0062] This preferred embodiment provides a morphological vehicle logo segmentation method, Figure 4 It is a flow chart of morphological vehicle logo segmentation according to an embodiment of the present invention, such as Figure 4 As shown, the method includes the following steps S402 to S414.

[0063] Step S402: Input a car image.

[0064] Step S404: license plate location. This step can adopt the implementation modes in the above preferred embodiments.

[0065] Step S406: Coarse positioning of the vehicle logo.

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 detecting method and a device of a vehicle logo. The method comprises that a region can be confirmed as a license plate region on a vehicle grayscale image, wherein the region can meet edge density reserved requirements after edge segmentation operation; a vehicle logo region is positioned with using license plate information and the license plate region and the vehicle logo is detected by using edge detection and watershed segmentation in the vehicle logo region. The accuracy of detecting the vehicle logo is improved through the detecting method and the device of the vehicle logo.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to a vehicle logo detection method and device Background technique [0002] With the development of social economy and the increase of vehicles, it is inevitable to manage vehicles through computer information and intelligence. License plate recognition technology is widely used in traffic flow monitoring, highway bayonet toll collection, red light violation vehicle monitoring and community automatic toll collection system. Current processing technology can only identify license plates and large, medium, and small vehicles, but not specific vehicle types. The recognition of the car logo is roughly divided into three steps: rough positioning of the car logo, fine positioning of the car logo, and recognition of the car logo. The precise positioning and segmentation of car logos is the most important step in car logo recognition. At present, the common shapes of car...

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): G06K9/54G06K9/32
Inventor 王海峰王晓萌何小波董博杨宇张凯歌
Owner 信帧机器人技术(北京)有限公司
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