Methods and devices for processing images

Patent metadata

Field	Value
Publication number	US-11399167-B2
Application number	US-202016852575-A
Country	US
Kind code	B2
Filing date	Apr 20, 2020
Priority date	Oct 19, 2017
Publication date	Jul 26, 2022
Grant date	Jul 26, 2022

Abstract

A system and a method for processing images are provided. The method may include one or more of the following operations. An image including a plurality of channels and a plurality of pixels may be obtained, each pixel having a pixel value corresponding to one of the plurality of channels. One of the plurality of pixels may be selected as a pixel of interest, and the corresponding channel of the pixel value of the pixel of interest may be designated as a target channel. A plurality of pixels proximate to the pixel of interest may include at least two first reference pixels. For each first reference pixel, a pseudo pixel value for the target channel of the first reference pixel may be determined. Whether the image is a deteriorated image may be determined at least based on the pixel value of the pixel of interest and the determined pseudo pixel values.

First claim

What is claimed is:

1. A system for image restoration processing, comprising:
a storage device storing an image acquired by an image sensor, the obtained image including a plurality of channels and a plurality of pixels, each pixel having a pixel value corresponding to one of the plurality of channels; and
at least one processor, wherein during operation, the at least one processor is configured to:
select one of the plurality of pixels as a pixel of interest;
designate the corresponding channel of the pixel value of the pixel of interest as a target channel;
select a plurality of pixels proximate to the pixel of interest, wherein the plurality of pixels proximate to the pixel of interest include at least two first reference pixels, wherein the first reference pixels have pixel values corresponding to a same first reference channel different from the target channel;
for each first reference pixel, determine a pseudo pixel value for the target channel of the first reference pixel;
determine that the pixel of interest is deteriorated at least based on the pixel value of the pixel of interest, and the determined pseudo pixel values of the first reference pixels for the target channel; and
create, upon a determination that the pixel of interest is deteriorated, a restored image.

2. The system of claim 1 , wherein the at least one processor is configured to:
select at least two second reference pixels within the plurality of pixels proximate to the pixel of interest, each second reference pixel having a pixel value corresponding to the target channel; and
determine that the pixel of interest is deteriorated at least based on the pixel value of the pixel of interest, the determined pseudo pixel values for the target channel of the first reference pixels, and the pixel values of the second reference pixels.

3. The system of claim 2 , wherein the at least one processor is configured to:
select at least two third reference pixels within the plurality of pixels proximate to the pixel of interest, wherein the third reference pixels have pixel values corresponding to a same second reference channel different from the target channel and the first reference channel;
for each third reference pixel, determine a pseudo pixel value for the target channel of the third reference pixel; and
determine that the pixel of interest is deteriorated based on the pixel value of the pixel of interest, the determined pseudo pixel values for the target channel of the first reference pixels, the pixel values of the second reference pixels, and the determined pseudo pixel values for the target channel of the third reference pixels.

4. The system of claim 3 , wherein the at least one processor is configured to:
determine a maximum pixel value among the determined pseudo pixel values for the target channel of the first reference pixels, the pixel values of the second reference pixels, and the determined pseudo pixel values for the target channel of the third reference pixels;
determine a difference between the pixel value of the pixel of interest and the maximum pixel value;
determine that the pixel of interest is deteriorated at least based on that the pixel value of the pixel of interest is larger than the maximum pixel value, and that the difference between the pixel value of the pixel of interest and the maximum pixel value exceeds a threshold.

5. The system of claim 3 , wherein the at least one processor is configured to:
determine a minimum pixel value among the determined pseudo pixel values for the target channel of the first reference pixels, the pixel values of the second reference pixels, and the determined pseudo pixel values for the target channel of the third reference pixels;
determine a difference between the pixel value of the pixel of interest and the minimum pixel value;
determine that the pixel of interest is deteriorated at least based on that the pixel value of the pixel of interest is smaller than the minimum pixel value, and that the difference between the pixel value of the pixel of interest and the minimum pixel value exceeds a threshold.

6. The system of claim 1 , wherein the pixel of interest and the plurality of pixels proximate to the pixel of interest are in a region, and the at least one processor is configured to:
determine a color difference corresponding to the region; and
for each first reference pixel in the region, determine the pseudo pixel value for the target channel of the first reference pixel based on the pixel value of the first reference pixel and the color difference corresponding to the region.

7. The system of claim 6 , wherein the at least one processor is configured to:
for each pixel in the region, determine a color difference value corresponding to the pixel;
determine a mean of the color difference values corresponding to the pixels in the region as the color difference corresponding to the region.

8. The system of claim 7 , wherein the at least one processor is configured to:
for one first reference pixel, select at least two pixels corresponding to the target channel and adjacent to the first reference pixel;
determine a mean of the pixel values of the selected pixels;
determine a difference between the pixel value of the first reference pixel and the determined mean as the color difference corresponding to the first reference pixel.

9. The system of claim 1 , wherein the at least one processor is further configured to:
correct the pixel value of the pixel of interest at least based on the determined pseudo pixel values for the target channel of the first reference pixels.

10. The system of claim 9 , wherein the at least one processor is configured to:
select a second reference pixel pair adjacent to the pixel of interest and a first reference pixel pair adjacent to the pixel of interest in the first reference pixels;
determine a first difference between pseudo pixel values for the target channel of the two pixels in the second reference pixel pair;
determine a second difference between pseudo pixel values for the target channel of the two pixels in the first reference pixel pair;
upon determining that the first difference is smaller than the second difference, correct the pixel value of the pixel of interest as one of the pseudo pixel values for the target channel of the two pixels of the first reference pixel pair.

11. The system of claim 1 , wherein the pixel of interest and the plurality of pixels are in a region centered on the pixel of interest.

12. A system for processing images, comprising at least one processor, wherein during operation, the at least one processor is configured to:
obtain an image including a plurality of pixels;
select one of the plurality of pixels as a pixel of interest;
select a first region and a second region according to the pixel of interest;
perform a false color correction operation on the pixel of interest based on at least some of a plurality of pixels in the first region to determine a first correction value for the pixel of interest, the first correction value being relating to the false color in the pixel of interest;
perform a color noise suppression operation on the pixel of interest based on at least some of a plurality of pixels in the second region to determine a second correction value for the pixel of interest, the second correction value being relating to the color noise in the pixel of interest;
determine a target correction value for the pixel of interest at least based on the determined first correction value and the second correction value; and
correct the pixel of interest based on the determined target correction value.

13. The s

Assignees

• Zhejiang Dahua Technology Co

Inventors

• Ling Chen
• Zhang Dan
• Ma Xin
• Fang Wei

Classifications

• H04N9/646 Primary

  for image enhancement, e.g. vertical detail restoration, cross-colour elimination, contour correction, chrominance trapping filters · CPC title

• H04N25/611

  Correction of chromatic aberration · CPC title

• H04N23/10

  for generating image signals from different wavelengths · CPC title

• H04N9/04

  Electricity · mapped topic