Frame classification license plate anti-counterfeiting method, device and equipment and storage medium

A license plate and border technology, applied in the field of deep learning, can solve problems such as weak robustness, failure of anti-counterfeiting methods, and poor anti-counterfeiting effects, and achieve the effect of strong robustness, reducing labeling costs, and ensuring accuracy

Pending Publication Date: 2022-05-17
CHENGDU VISION ZENITH TECH DEV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The common point of these traditional image processing algorithms is to extract certain general features, and these features are artificially designed features, which are only suitable for scenes with relatively specific external conditions and weak robustness.
Once the background is complicated, such as light interference, rain and snow, traditional anti-counterfeiting methods will be affected by environmental factors and cause failure
[0005] In addition, there is also a method of anti-counterfeiting by posting various two-dimensional barcodes, which not only brings additional cost overhead, but also does not get rid of the disadvantages of traditional algorithms, and the anti-counterfeiting effect is still not good

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
  • Frame classification license plate anti-counterfeiting method, device and equipment and storage medium
  • Frame classification license plate anti-counterfeiting method, device and equipment and storage medium
  • Frame classification license plate anti-counterfeiting method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] The license plate anti-counterfeiting method of border classification provided in this embodiment uses a deep learning model to first locate and then automatically classify the authenticity of the license plate. The process of the whole function is: ① input frame, ② license plate detection and positioning module, ③ license plate ROI (Region of Interesting) with different proportions, ④ anti-counterfeiting classification model, ⑤ output authenticity.

[0043] refer to figure 1 ,Such as figure 1 Shown is a schematic flow chart of the anti-counterfeiting method for the frame classification license plate provided by this embodiment. The method specifically includes the following steps:

[0044] Step S100: Acquiring pictures of vehicles passing by with real license plates and pictures of passing vehicles with fake license plates.

[0045] Specifically, through the license plate recognition cameras at each bayonet, the pictures of real cars passing by and fake license plat...

Embodiment 2

[0062] refer to Figure 6 ,Such as Figure 6 Shown is a structural block diagram of the frame classification license plate anti-counterfeiting device provided by this embodiment.

[0063] The device specifically includes a license plate image acquisition module, which is used to acquire pictures of passing vehicles with real license plates and pictures of passing vehicles with fake license plates.

[0064] The license plate image labeling module is used to mark the license plate frame of the real license plate passing car picture and the fake license plate passing car picture, and mark the real license plate passing car picture as true, and mark the fake license plate passing car picture as false.

[0065] The building block of the license plate location model is used to train the marked pictures of passing vehicles to obtain the license plate location model.

[0066] The license plate clipping module is used to obtain the image of the license plate frame to be detected, cut...

Embodiment 3

[0076] This preferred embodiment provides a computer device, which can implement the steps in any embodiment of the frame classification license plate anti-counterfeiting method provided in the embodiment of the present application, therefore, the frame classification license plate provided in the embodiment of the present application can be realized For the beneficial effects of the anti-counterfeiting method, see the previous embodiments for details, and will not be repeated here.

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 frame classification license plate anti-counterfeiting method, device and equipment and a storage medium. The method comprises the following steps: acquiring a real license plate vehicle passing picture and a false license plate vehicle passing picture; carrying out license plate frame labeling on the real license plate vehicle-passing picture and the false license plate vehicle-passing picture, labeling the real license plate vehicle-passing picture as real, and labeling the false license plate vehicle-passing picture as false; training the marked vehicle passing pictures to obtain a license plate positioning model; obtaining an image of a to-be-detected license plate frame, and cutting the image of the to-be-detected license plate frame to obtain a first to-be-detected license plate frame, a second to-be-detected license plate frame and a third to-be-detected license plate frame; and performing true and false detection on the first to-be-detected license plate frame, the second to-be-detected license plate frame and the third to-be-detected license plate frame according to the true and false license plate classification model, and if the first to-be-detected license plate frame, the second to-be-detected license plate frame and the third to-be-detected license plate frame are detected to be true, judging that the to-be-detected license plate frames are true. Whether the license plate has the container frame feature is judged by using a method of positioning and then classifying.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to a frame classification license plate anti-counterfeiting method, device, equipment and storage medium. Background technique [0002] With the development of technology, unattended parking has become the mainstream mode of parking lot. Due to the lack of supervision of on-site personnel, the phenomenon of artificial fee evasion has increased. A reliable anti-counterfeiting function plays a very important role in parking lot management. [0003] From a technical point of view, the license plate recognition of the barrier gate only has the function of character recognition, and the recognition function treats the real license plate, mobile phone license plate or printed license plate equally, so the phenomenon of artificial evasion is very common. [0004] In view of this problem, the existing license plate anti-counterfeiting methods rely on the physical reflect...

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): G06V20/62G06V10/26G06V10/764G06K9/62
CPCG06F18/24
Inventor 杨双祥任鹏周卓立
Owner CHENGDU VISION ZENITH TECH DEV
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