Device, method, smart glasses for color vision deficiency correction

Patent metadata

Field	Value
Publication number	US-11657545-B2
Application number	US-202117225760-A
Country	US
Kind code	B2
Filing date	Apr 8, 2021
Priority date	Apr 13, 2020
Publication date	May 23, 2023
Grant date	May 23, 2023

Abstract

The present invention relates to a device, method, and smart glasses for color vision deficiency correction. The method includes: adjusting a color of an image according to an environmental color temperature to obtain an adjusted image, and then adjusting a pixel level of the adjusted image to a preset pixel level according to image content, to obtain a to-be-processed image; determining an adjustment matrix based on an RGB value of the to-be-processed image and a preset RGB target value; comparing a color displayed on a display with a color of a standard colorimetric card for correction, to determine an adjustment mapping table; and generating a target image based on the to-be-processed image, the adjustment matrix, and the adjustment mapping table. The present invention increases the degree of color recognition and improves imaging effects, and can implement good color vision deficiency correction.

First claim

What is claimed is:

1. A color vision deficiency correction method, comprising:
adjusting a color of an image according to an environmental color temperature to obtain an adjusted image, and then adjusting a pixel level of the adjusted image to a preset pixel level according to image content, to obtain a to-be-processed image;
determining an adjustment matrix based on an RGB value of the to-be-processed image and a preset RGB target value;
comparing a color displayed on a display with a color of a standard colorimetric card for correction, to determine an adjustment mapping table; and
generating a target image based on the to-be-processed image, the adjustment matrix, and the adjustment mapping table,
wherein the adjusting a pixel level of the adjusted image to a preset pixel level comprises: performing inverse tone mapping on a preset key frame of the adjusted image, and performing motion estimation on frames other than the preset key frame so as to adjust the pixel level of the adjusted image to the preset pixel level, wherein one frame is processed for every preset number of frames of the adjusted image, and the processed frame is the key frame; and
using a first neural network to perform inverse tone mapping on the preset key frame of the adjusted image, and using an optical flow method to perform motion estimation on the frames other than the preset key frame, wherein the first neural network is a neural network with an encoder-decoder architecture.

2. The color vision deficiency correction method according to claim 1 , wherein
the color of the image captured by a camera is adjusted according to the environmental color temperature, and the RGB value of the image captured by the camera is adjusted by using the following formula:

R
=

{

2
⁢
5
⁢
5

,

T
≤

6
⁢
6

3
⁢
2
⁢

9
.
6

⁢
9
⁢
8
⁢
7
*

(

T
-

6
⁢
0

)

-
0.133

,

T
>

6
⁢
6

⁢

⁢
G

=

{

9
⁢

9
.
4

⁢
7
*

⁢
ln
⁢
T

-

1
⁢
6
⁢

1
.
1

⁢
1
⁢
9
⁢
5

,

T
≤

6
⁢
6

2
⁢
8
⁢

8
.
1

⁢
2
*

(

T
-

6
⁢

Assignees

• Yutou Tech Hangzhou Co Ltd

Inventors

• Zhu Haichao
• Chen Yiming

Classifications

• G06T11/10 Primary

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06T2207/10024

  Color image · CPC title

• G09G5/02

  characterised by the way in which colour is displayed {(details of colour display specific for CRTs G09G1/28; specific for flat matrix panels other than liquid crystal displays G09G3/2003; specific for liquid crystal displays G09G3/3607)} · CPC title

• G02B27/0172

  characterised by optical features · CPC title

• G02B2027/0178

  Eyeglass type (eyeglass details G02C) · CPC title