Image enhancement processing method, device, equipment, and medium based on artificial intelligence

Patent metadata

Field	Value
Publication number	US-12014498-B2
Application number	US-202017613482-A
Country	US
Kind code	B2
Filing date	Aug 30, 2020
Priority date	Jul 31, 2020
Publication date	Jun 18, 2024
Grant date	Jun 18, 2024

Abstract

An image enhancement processing method includes: acquiring an initial image, preprocessing the initial image, and acquiring an original feature image containing a target feature; performing an edge detection on the original feature image using an edge detection algorithm to obtain an original gradient image, obtaining a statistics ring based on the original feature image, and performing an iterative process on the statistics ring; obtaining a to-be-processed image based on an inner diameter of on the statistics ring, and determining to-be-processed parameters of the to-be-processed image: acquiring a standard image corresponding to the target feature, determining a standard area corresponding to the standard image, and acquiring standard image parameters corresponding to the standard area; performing a migration process on the to-be-processed image to obtain a migration image; and performing a restricted contrast adaptive histogram equalization process on the migration image to obtain a target enhanced image.

First claim

What is claimed is:

1. An image enhancement processing method based on artificial intelligence, comprising:
acquiring an initial image, preprocessing the initial image, and acquiring an original feature image containing a target feature;
performing an edge detection on the original feature image using an edge detection algorithm to obtain an original gradient image, obtaining a statistics ring based on the original feature image, and performing an iterative process on the statistics ring; when the statistics ring intersects with the original gradient image, cropping the original feature image to obtain a to-be-processed image based on an inner diameter of on the statistics ring, and determining to-be-processed parameters of the to-be-processed image:
acquiring a standard image corresponding to the target feature, determining a standard area corresponding to the standard image, and acquiring standard image parameters corresponding to the standard area; performing a migration process on the to-be-processed image according to the to-be-processed parameters and the standard image parameters to obtain a migration image; and
performing a restricted contrast adaptive histogram equalization process on the migration image to obtain a target enhanced image.

2. The image enhancement processing method of claim 1 , wherein performing an edge detection on the original feature image using an edge detection algorithm to obtain an original gradient image, obtaining a statistics ring based on the original feature image, and performing an iterative process on the statistics ring; when the statistics ring intersects with the original gradient image, cropping the original feature image to obtain a to-be-processed image based on an inner diameter of on the statistics ring, and determining to-be-processed parameters of the to-be-processed image comprises:
calculating a horizontal gradient in a horizontal direction and a vertical gradient in a vertical direction in the original feature image by using Sobel algorithm;
weighting the horizontal gradient and the vertical gradient to obtain an original gradient image;
obtaining the statistics ring according to a length of a long side of the original feature image and a preset distance;
performing a reduction iterative process on an inner diameter of the statistics ring to obtain an iterative gradient value corresponding to the statistics ring;
if the iterative gradient value is greater than a preset gradient value, determining that the inner diameter of the statistics ring intersects with the original gradient image, and determining the inner circle of the statistics ring as the to-be-processed image.

3. The image enhancement processing method of claim 1 , wherein performing a migration process on the to-be-processed image according to the to-be-processed parameters and the standard image parameters to obtain a migration image comprises:
acquiring each to-be-processed pixel of the to-be-processed image;
processing the to-be-processed pixel, the to-be-processed parameters, and the standard image parameters by using a migration formula to obtain a migration pixel corresponding to the to-be-processed pixel; and
forming the migration image based on the migration pixels.

4. The image enhancement processing method of claim 3 , wherein the to-be-processed parameters comprise an average value of the to-be-processed pixels and a variance of the to-be-processed pixels; the standard image parameters comprise a standard pixel average and a standard pixel variance;
the processing the to-be-processed pixel, the to-be-processed parameters, and the standard image parameters by using a migration formula to obtain a migration pixel corresponding to the to-be-processed pixel comprises:
placing the to-be-processed pixels, the average value of the to-be-processed pixels, the variance of the to-be-processed pixels, the standard pixel average, and the standard pixel variance into the migration formula, and obtaining the migration pixel corresponding to the to-be-processed pixels.

5. The image enhancement processing method of claim 1 , wherein the performing a restricted contrast adaptive histogram equalization process on the migration image to obtain a target enhanced image comprises:
acquiring a corresponding channel image based on the migration image;
performing a blocking process on the channel image to obtain a to-be-processed block image;
processing the to-be-processed block image using a histogram function, and obtaining a block histogram corresponding to the to-be-processed block image;
cropping the block histogram based on a preset threshold to obtain the cropped histogram, equalizing the cropped histogram to obtain the target enhanced image.

6. The image enhancement processing method of claim 5 , wherein cropping the block histogram based on a preset threshold to obtain the cropped histogram comprises:
acquiring a gray value corresponding to the to-be-processed block image;
evenly distributing the gray values higher than the preset threshold to all the block histograms and obtaining the cropped histogram.

7. The image enhancement processing method of claim 1 , wherein before the acquiring an original feature image containing a target feature; the image enhancement processing method further comprises:
acquiring a verification image and at least two candidate images corresponding to the verification image; performing the steps of claim 1 to process the verification image, and obtaining an image to be tested corresponding to the verification image;
inputting the image to be tested into a MaskRCNN model generated based on the candidate image corresponding to the image to be tested for detection, and obtaining a detection result;
according to the detection result, determining a detection accuracy of each candidate image, and determining the candidate image with the highest detection accuracy as a standard image.

8. A computer equipment comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein, when being executed by the processor, the computer program implements following steps:
acquiring an initial image, preprocessing the initial image, and acquiring an original feature image containing a target feature;
performing an edge detection on the original feature image using an edge detection algorithm to obtain an original gradient image, obtaining a statistics ring based on the original feature image, and performing an iterative process on the statistics ring; cropping the original feature image to obtain a to-be-processed image when the statistics ring intersects with the original gradient image, and determining to-be-processed parameters of the to-be-processed image;
acquiring a standard image corresponding to the target feature, determining a standard area corresponding to the standard image, and acquiring standard image parameters corresponding to the standard area; performing a migration process on the to-be-processed image according to the to-be-processed parameters and the standard image parameters to obtain a migration image; and
performing a restricted contrast adaptive histogram equalization process on the migration image to obtain a target enhanced image.

9. The computer equipment of claim 8 , wherein the performing an edge detection on the original feature image using an edge detection algorithm to obtain an original gradient image, obtaining a statistics ring based on the original feature image, and performing an iterative process on the statistics ring; when the statistics ring intersects with the original gradient image, cropping the original feature image to obtain a to-be-processed image based on an inner diameter of on the statistics

Assignees

• Ping An Tech Shenzhen Co Ltd

Inventors

• Fan Dongyi
• Wang Rui
• Wang Lilong

Classifications

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T5/40 Primary

  using histogram techniques · CPC title

• G06T7/13

  Edge detection · CPC title

• G06T5/60

  using machine learning, e.g. neural networks · CPC title

• G06T7/174

  involving the use of two or more images · CPC title