Supercharge Your Innovation With Domain-Expert AI Agents!

Two-dimensional code super-resolution reconstruction enhancement method and system based on deep learning

A technology of deep learning and two-dimensional code, which is applied in the field of two-dimensional code super-resolution reconstruction enhancement method and system, can solve problems such as inability to directly scan two-dimensional codes, difficult to meet application scenarios, and uneven effects, etc., to achieve improved Scan recognition rate, improve image enhancement effect, improve the effect of enhancement effect

Pending Publication Date: 2021-03-30
CHENGDU UNION BIG DATA TECH CO LTD
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is that there are large differences in the resolution and blurring degree of the license pictures acquired in natural scenes, which leads to the fact that in some scenes, due to the low resolution of the two-dimensional code image, it is impossible to directly scan the two-dimensional The traditional method is to perform super-resolution methods such as bilinear interpolation on the two-dimensional code area to upsample it to improve the resolution of the two-dimensional code image. However, due to the complexity of natural scenes, etc. , resulting in uneven effects of directly using bilinear interpolation and other image upsampling methods, which is difficult to meet the needs of actual application scenarios

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
  • Two-dimensional code super-resolution reconstruction enhancement method and system based on deep learning
  • Two-dimensional code super-resolution reconstruction enhancement method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] like figure 1 , figure 2 As shown, the present invention is a two-dimensional code super-resolution reconstruction enhancement method based on deep learning, and the method comprises the following steps:

[0044] Step 1: Collect high-resolution images containing QR codes and store them; among them: divide the collected images into three parts: training set, verification set and test set according to a certain ratio; down-sample and save the collected images respectively to the image database;

[0045] Step 2: constructing a QRSR super-resolution network model for upsampling image enhancement to low-resolution two-dimensional code images, and utilizing the training data set stored in the image database to train the QRSR super-resolution network model;

[0046] Step 3: Pruning and quantizing the QRSR super-resolution network model to obtain a compressed QRSR super-resolution network model; wherein: firstly, the trained QRSR super-resolution network model is pruned, and...

Embodiment 2

[0064] like figure 1 , figure 2 As shown, the difference between this embodiment and Embodiment 1 is that this embodiment provides a two-dimensional code super-resolution reconstruction enhancement system based on deep learning, which supports the deep learning-based system described in Embodiment 1. Two-dimensional code super-resolution reconstruction enhancement method, the system includes:

[0065] The acquisition and storage unit is used to collect high-resolution two-dimensional code pictures taken under different natural scenes, and perform s times downsampling on the high-resolution two-dimensional code picture, where s=4; and the processed high-resolution Divide and store the corresponding low-resolution two-dimensional code image into a training data set, a verification data set and a test data set;

[0066] Model construction and training unit, construct QRSR super-resolution network model, input the low resolution and corresponding high-resolution two-dimensional...

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 two-dimensional code super-resolution reconstruction enhancement method and system based on deep learning. The method comprises the steps of 1, collecting and storing a high-resolution picture containing a two-dimensional code, and respectively carrying out down-sampling processing on the collected pictures and storing the pictures in an image database; 2, constructing aQRSR super-resolution network model, and training the model; 3, pruning and quantizing the QRSR super-resolution network model to obtain a compressed model; 4, obtaining a low-resolution two-dimensional code picture, and inputting the picture into the compressed model, wherein the output of the QRSR super-resolution network model is a high-resolution two-dimensional code image; and 5, conducting gray processing on the high-resolution two-dimensional code image acquired in the step 4, conducting image opening operation on the gray-scale map, and storing the processed high-resolution two-dimensional code gray-scale map. According to the invention, the recognition rate of the computer in recognizing the low-resolution two-dimensional code image information in a real scene is improved.

Description

technical field [0001] The invention relates to the technical field of image enhancement, in particular to a two-dimensional code super-resolution reconstruction enhancement method and system based on deep learning. Background technique [0002] Since the invention of QR code technology, it has been widely used in all walks of life because of its convenience and ease of use. For example, business licenses, food business licenses, etc. all contain QR codes, which can be scanned by image input devices such as mobile phone cameras. The processing of information can be realized automatically, so as to obtain the relevant text information in the license picture. However, due to the large differences in the resolution and blurring degree of the license pictures obtained in natural scenes, it is impossible to directly scan the two-dimensional code and extract the information in some scenes due to the low resolution of the two-dimensional code image , the traditional method is to u...

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): G06K7/14G06T3/40G06T7/11G06N3/08G06N3/04
CPCG06K7/146G06T3/4053G06T7/11G06N3/08G06T2207/20081G06N3/045
Inventor 不公告发明人
Owner CHENGDU UNION BIG DATA 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