Image denoising method based on convolution templates
A convolution template and image technology, applied in the field of image processing, can solve problems such as unfavorable hardware implementation, poor weakening effect of isolated noise points, and complicated calculation process.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] See figure 1 , figure 1 It is a schematic flowchart of an image denoising method based on a convolution template provided by an embodiment of the present invention. The image denoising method based on the convolution template includes:
[0044] S1. Obtain a preprocessed image by preprocessing the original image;
[0045] S2. Obtain an output image by performing convolution and denoising on the preprocessed image;
[0046] S3. Obtain a denoised image by correcting the output image.
[0047] Wherein, for step S1, may include:
[0048] S11. Perform mirror extension on the outermost circle data of the original image to obtain a preprocessed image.
[0049] Wherein, for step S2, may include:
[0050] S21. Calculate the weight coefficient;
[0051] S22. Obtain a filtered image by using the filtering template and the preprocessed image;
[0052] S23. Acquire the output image according to the weight coefficient and the filtered image.
[0053] Wherein, for step S21, ma...
Embodiment 2
[0075] Please refer to figure 2 , figure 2 It is a schematic flowchart of another image denoising method based on a convolution template provided by an embodiment of the present invention. This embodiment further describes the image denoising method in detail on the basis of the above embodiments, wherein the image denoising method takes a preset template with a size of 3*3 as an example, and specifically includes the following steps:
[0076] Step 1: Perform mirror expansion on the outermost circle data of the original image;
[0077] The original image containing noise is recorded as I, and the outermost circle data (the first row, the first column, the last row, and the last column) of the original image are mirrored and extended to obtain a preprocessed image, which is recorded as I_input.
[0078] Step 2: Extract edge information of the preprocessed image;
[0079] Convolute with I_input through four preset templates to extract the edge information of the preprocessed ...
Embodiment 3
[0122] Please continue to see figure 2 , figure 2 It is a schematic flowchart of another image denoising method based on a convolution template provided by an embodiment of the present invention. This embodiment further describes the image denoising method in detail on the basis of the above embodiments, wherein the image denoising method takes a preset template with a size of 5*5 as an example, and specifically includes the following steps:
[0123] Step 1: Perform mirror expansion on the outermost circle data of the original image;
[0124] The original image containing noise is recorded as I, and the outermost circle data (the first row, the first column, the last row, and the last column) of the original image are mirrored and extended to obtain a preprocessed image, which is recorded as I_input.
[0125] Step 2: Extract edge information of the preprocessed image;
[0126] Convolute with I_input through eight preset templates to extract the edge information of the pre...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


