A denoising method for damaged images of carbon fiber plates
By performing image scaling and one-dimensional Gaussian convolution operations on damaged images of carbon fiber boards, the problems of poor Gaussian blur effect and high computational complexity in the prior art are solved, and better blur effect and faster computing speed are achieved.
CN114529471BActive Publication Date: 2025-03-21ZHEJIANG SCI-TECH UNIV
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202210156876.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-02-21
- Publication Date
- 2025-03-21
- Estimated Expiration
- 2042-02-21
AI Technical Summary
Technical Problem
In the prior art, when processing damaged images of carbon fiber boards, Gaussian blurring is poor, the calculation complexity is high, resulting in slow computing speed.
Method used
By scaling the image to be processed, the amount of data is reduced, and then performing one-dimensional Gaussian convolution operation, first performing convolution in the horizontal direction, then performing convolution in the vertical direction, and finally enlarging the image to its original size.
Benefits of technology
Improves Gaussian blur effect, reduces the computational complexity and operational volume, significantly speeds up the running speed, and avoids the possible jagging after image scaling.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention discloses a denoising method for a damaged image of a carbon fiber plate. The method mainly uses Gaussian blur to denoise the image. First, the main body of the image is halved to reduce the amount of data to be processed, so that the denoising effect of the image is more significant. Secondly, convolution is performed on the processed image, and the original two-dimensional Gaussian convolution of the Gaussian blur is divided into two one-dimensional Gaussian convolution operations, firstly performing convolution horizontally and then performing convolution vertically. Finally, the blurred image is reduced to its original size. Compared with ordinary Gaussian blur, the method is more obvious in denoising the image and also plays a certain role in the rapid realization of Gaussian blur.
Need to check novelty before this filing date? Find Prior Art