Unlock instant, AI-driven research and patent intelligence for your innovation.

Batch graphic code recognition method and device based on deep learning, and storage medium

A deep learning and recognition method technology, applied in the field of batch processing of graphic codes, can solve problems such as missing scans, long time-consuming scanning codes, prone to re-scanning, etc., to achieve the effect of ensuring accuracy and ensuring accuracy

Inactive Publication Date: 2021-12-03
INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using a code scanner to collect graphic code information of materials is inefficient. When there are a large number of materials and a large amount of graphic code data needs to be collected, it takes a long time to scan the code with a code scanner, and it is easy to re-scan or miss-scan. Additional checks for duplicates and leaks
Seriously affect and restrict the efficient progress of the production process

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
  • Batch graphic code recognition method and device based on deep learning, and storage medium
  • Batch graphic code recognition method and device based on deep learning, and storage medium
  • Batch graphic code recognition method and device based on deep learning, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] The embodiment of this application provides a batch pattern code recognition method based on deep learning, refer to figure 1 As shown, the batch pattern code recognition method based on deep learning comprises:

[0050] S100. Collect and process a batch of graphic code images to obtain a target image, where the target image includes at least one graphic code.

[0051] Specifically, see figure 2 As shown, collecting and processing batches of graphic code images to obtain target images includes:

[0052] S101, collect the video of the graphic code carrier through video equipment, and the graphic code carrier contains batches of graphic codes; when applied in the process of material graphic code identification, the graphic code carrier is the corresponding graphic code label on the material, and the graphics on the material The code labels are uniformly oriented, and the graphic codes of batch materials are collected through video equipment. During video capture, the ...

Embodiment 2

[0087] The embodiment of this application provides a device for batch pattern code recognition based on deep learning, refer to Figure 4 As shown, the device for batch pattern code recognition based on deep learning includes:

[0088]A collection module, the collection module is used to collect video of a batch of graphic codes; specifically, the collection module is configured in a video device.

[0089] An image processing module, the image processing module obtains video from the acquisition module, and obtains several images from video frames, and calculates the definition of the image; selects the image with the highest definition to form the target image;

[0090] The first graphic code extraction module, the first graphic code extraction module realizes the first graphic code extraction model, obtains the target image from the image processing module, and extracts the graphic code from the target image one by one to form the first group of graphic codes;

[0091] The ...

Embodiment 3

[0098] An embodiment of the present application provides a storage medium for realizing a batch pattern code recognition method based on deep learning. The storage medium for realizing the batch pattern code recognition method based on deep learning stores at least one instruction, and executing the instruction realizes the batch pattern code recognition method based on deep learning.

[0099] The first graphic code extraction model of the present application and the second graphic code extraction module run in parallel to realize graphic code extraction for the same target image respectively, and the process of decoding the first group of graphic codes is the same as that of the second group The process of graphic code decoding is carried out in parallel; so that the parsing results of the graphic code extracted by the first graphic code extraction model and the second graphic code extraction module from the same target image can be mutually verified. This enables the applica...

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 batch graphic code recognition method and device based on deep learning, and a storage medium. The method comprises the following steps: collecting videos of batch graphic codes, decomposing the videos frame by frame to obtain images of a plurality of batch graphic codes, calculating the definition of the images, selecting the image with the highest definition as a target image, and inputting the target image into a first graphic code extraction model and a second graphic code extraction model which can identify bar shapes through training for identification and extraction of the graphic codes; and extracting graphic codes from an image containing batch graphic codes one by one, analyzing single graphic codes extracted by a first graphic code extraction model and a second graphic code extraction model, comparing analysis results, if the analysis results are consistent, judging that the graphic codes are extracted and analyzed correctly, and if the analysis results are not consistent, outputting extraction and analysis errors. The graphic code analysis result can be self-verified, and the first graphic code extraction model and the second graphic code extraction model are retrained when analysis errors are frequently extracted.

Description

technical field [0001] The present application relates to the field of batch processing of graphic codes, in particular to a deep learning-based batch graphic code recognition method, device and storage medium. Background technique [0002] Graphical code is a graphic representing data information formed by specific geometric figures according to set rules. Graphical code is widely used in material management and other fields. [0003] For the server production process, each material of the production server, especially the electronic components, needs to be equipped with a unique identification code, which will be accompanied until the material is scrapped. The identification code is often represented by a graphic code. In reproduction, each material processing process needs to be recorded in detail in the production management system, and the graphic code information of the material often needs to be collected before or after the processing link. General staff scan the g...

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): G06K7/14G06N3/04G06N3/08
CPCG06K7/14G06N3/08G06N3/045
Inventor 华逢友
Owner INSPUR SUZHOU INTELLIGENT TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com