Unlock instant, AI-driven research and patent intelligence for your innovation.

Image processing method and device

An image processing and image technology, applied in the field of neural networks, can solve the problems that the algorithm cannot define the processing area, the artifact removal effect is difficult to control, and the image is distorted, so as to improve the effect of the artifact removal effect.

Pending Publication Date: 2022-07-29
SONOSEMI MEDICAL CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, some algorithms based on Generative Adversarial Networks (GAN) can directly process images containing artifacts and directly output images without artifacts, but this type of algorithm against generative models cannot define the processing area. When the generated model excessively repairs the dark area of ​​the image, the image will be distorted, and the artifact removal effect is difficult to control

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
  • Image processing method and device
  • Image processing method and device
  • Image processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] An embodiment of the present invention provides an image processing method, see figure 1 The flow chart of an image processing method shown, the image processing method includes the following steps:

[0031] Step S102, acquiring images of RGB channels.

[0032] RGB channels refer to the channels of three colors of red (Red), green (Green), and blue (Blue), which can be obtained by changing the three color channels of red, green, and blue and superimposing them on each other. Images in various colors.

[0033] Step S104, preprocess the image of the RGB channel to obtain the image of the mask channel.

[0034] The preprocessing in this embodiment may include processing methods such as removing watermarks, transforming coordinates, scrolling on the vertical axis, and removing afterimages. In addition, the preprocessing of this embodiment can also generate a random mask, and perform dot multiplication with the image through the random mask to obtain the image of the mask...

Embodiment 2

[0041] The above method provided by the embodiment of the present invention is another image processing method, which is implemented on the basis of the method provided by the above embodiment. See figure 2 The flow chart of another image processing method shown, the image processing method includes the following steps:

[0042] Step S202, acquiring images of RGB channels.

[0043] Step S204, preprocess the image of the RGB channel to obtain the image of the mask channel.

[0044] Specifically, the images of the RGB channels can be preprocessed by the following steps: removing the watermark of the images of the RGB channels; performing polar coordinate transformation processing on the images of the RGB channels; performing vertical axis scrolling processing on the images of the RGB channels; Afterimage removal processing is performed on the image of the RGB channel; a random mask of the image of the RGB channel is generated, and the image of the mask channel is determined base...

Embodiment 3

[0095] Corresponding to the above method embodiments, the embodiments of the present invention provide an image processing apparatus, such as Figure 4 A schematic structural diagram of an image processing apparatus shown, the image processing apparatus includes:

[0096] The image acquisition module 41 is used for acquiring the image of RGB channel;

[0097] The image preprocessing module 42 is used to preprocess the image of the RGB channel to obtain the image of the mask channel;

[0098] The first sub-model processing module 43 is used to input the image of the RGB channel and the image of the mask channel into the first sub-model of the pre-trained generator, and output the rough patched image;

[0099] The second sub-model processing module 44 is configured to input the rough inpainted image into the second sub-model of the generator to obtain the fine inpainted image.

[0100] An image processing apparatus provided by an embodiment of the present invention obtains an ...

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 provides an image processing method and device, and relates to the technical field of neural networks. The method comprises the following steps: acquiring an image of an RGB channel; preprocessing the image of the RGB channel to obtain an image of a mask channel; inputting the image of the RGB channel and the image of the mask channel into a first sub-model of a pre-trained generator, and outputting a rough repairing image; and inputting the rough inpainting image into the second sub-model of the generator to obtain a fine inpainting image. According to the method, the image of the RGB channel is preprocessed to obtain the image of the mask channel, the mask area of the image of the mask channel is used as the target area, and the image of the mask channel is repaired through the first sub-model and the second sub-model of the generator, so that the fine repaired image can be obtained. In the mode, artifacts, shadows and the like of the target area in the image can be removed by defining the target area, and the artifact removal effect is improved.

Description

technical field [0001] The present invention relates to the technical field of neural networks, and in particular, to an image processing method and device. Background technique [0002] For the noise reduction of ultrasound images, there have been many studies in the prior art. At present, some algorithms based on Generative Adversarial Networks (GAN) can directly process images with artifacts and directly output images without artifacts, but such algorithms against generative models cannot define the processing area. When the generative model over-patches the dark areas of the image, the image will be distorted, and the removal of artifacts is difficult to control. SUMMARY OF THE INVENTION [0003] In view of this, the purpose of the present invention is to provide an image processing method and apparatus, so as to remove artifacts, shadows, etc. of the target area by defining a target area, so as to improve the effect of removing artifacts. [0004] In a first aspect,...

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): G06T5/00G06N3/04G06N3/08
CPCG06N3/088G06T2207/10024G06T2207/10132G06T2207/20081G06T2207/20084G06T2207/30168G06N3/045G06T5/77G06T5/70
Inventor 何好刘斌邬伽林
Owner SONOSEMI MEDICAL CO LTD