Two-dimensional code image generation method and apparatus, storage medium and electronic device

Patent metadata

Field	Value
Publication number	US-11164059-B2
Application number	US-202016835809-A
Country	US
Kind code	B2
Filing date	Mar 31, 2020
Priority date	Oct 17, 2018
Publication date	Nov 2, 2021
Grant date	Nov 2, 2021

Abstract

Disclosed is a two-dimensional code image generation method and apparatus, a storage medium and an electronic device related to the field of two-dimensional code image technology. The method includes obtaining an initial two-dimensional code image and a background image, and performing structured processing on the initial two-dimensional code image according to the background image to obtain a structured two-dimensional code image, performing mode transfer processing on the background image to obtain a background image of a target mode by a mode transfer model, and performing a fusion operation on the structured two-dimensional code image and the background image of the target mode to obtain a target two-dimensional code image.

First claim

What is claimed is:

1. A two-dimensional code image generation method, comprising:
obtaining an initial two-dimensional code image and a background image, and performing structured processing on the initial two-dimensional code image according to the background image to obtain a structured two-dimensional code image, wherein the structured processing is to fuse an image element of the background image on the premise of retaining the basic information of the initial two-dimensional code image, wherein the performing structured processing on the initial two-dimensional code image according to the background image to obtain a structured two-dimensional code image comprises: performing preprocessing on the background image to transform it to a corresponding scattergram which is constituted by a pixel module composed of black pixels and a pixel module composed of white pixels and of which the image size is the same as that of the initial two-dimensional code image; identifying individual functional areas of the initial two-dimensional code image, determining an area in the individual functional areas where pixel change may be made, determining the amount of change of a pixel in the area where the pixel change may be made in comparison with the scattergram, and generating the structured two-dimensional code image after corresponding change;
performing mode transfer processing on the background image to obtain a background image of a target mode by a mode transfer model for converting an input image to an image of the target mode; and
performing a fusion operation on the structured two-dimensional code image and the background image of the target mode to obtain a target two-dimensional code image, such that the target two-dimensional code image not only has the basic information and the image element, but also has the target mode.

2. The method as claimed in claim 1 , wherein the performing preprocessing on the background image to transform it to the corresponding scattergram comprises:
processing the background image into a corresponding grayscale image and dividing the grayscale image into (n/m) 2 pixel modules of the size m×m, the pixel module being denoted as sub G r , r being the index of a current pixel module and its value range being [1,(n/m) 2 ], wherein n is the size of the initial two-dimensional code image, m is the size of a unit black module or a unit white module of the initial two-dimensional code image, the initial two-dimensional code image is constituted by multiple unit black modules and unit white modules, performing binarization processing of sub G r to obtain binarized modules, the scattergram comprises (n/m) 2 binarized modules, wherein mod G r is a module after sub G r is binarized:

G
r

mod

=

round
⁢

{

∑

i
,
j

⁢

G
r

sub

⁡

(

i
,
j

)

·

G
W

⁡

(

i
,
j

)

255

}

wherein round represents an operation of taking value to the nearest whole number, G W (i, j) is a weight of sub G r at its pixel (i, j), 1=<i, j<=m, Σ i, j G W (i, j)=1, and G W (i, j) satisfies the Gaussian distribution and is defined as follows:

G
W

⁡

(

i
,
j

)

=

1

2
⁢
π
⁢

σ
2

⁢

e

-

i
2

+

j
2

2
⁢

σ
2

,

σ
=

m
-
1

6

wherein σ represents the standard deviation of the Gaussian distribution.

3. The method as claimed in claim 2 , wherein the structured processing comprises:
fusing the binarized background image with the initial two-dimensional code image to obtain an intermediate two-dimensional code image by the following formula:

Q
r
i

mod

=

{

Q
r
s

mod

,

Q

Assignees

• Boe Technology Group Co Ltd

Inventors

• Zhu Dan
• Navarrete Michelini Pablo
• Zhang Lijie
• Liu Hanwen

Classifications

• G06K19/06037 Primary

  multi-dimensional coding · CPC title

• G06K19/06103 Primary

  the marking being embedded in a human recognizable image, e.g. a company logo with an embedded two-dimensional code · CPC title

• H04N1/32101

  Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title · CPC title

• G06T1/0021

  Image watermarking · CPC title

• H04N1/32309

  in colour image data · CPC title