Image denoising method, device, equipment and storage medium
An image and image block technology, applied in the field of image processing, can solve the problems of unable to form training data, unable to obtain clean pictures, unable to achieve denoising effect, etc., to improve the denoising effect, reduce the dependence of prior knowledge, efficient and accurate The effect of removing noise
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 2
[0079] Embodiment two, see figure 2 , after the acquisition of the first noise image in the noise block set, before constructing the training set according to the noise image and the noise-free image, it also includes:
[0080] S21. Perform noise modeling on the noise block set according to the generative confrontation network, so as to obtain a generator that can generate the same type of noise as the image to be denoised;
[0081] S22. Acquire a second noise image according to the generator;
[0082] Then constructing a training set according to the first noise image and noise-free image includes:
[0083] S23. Construct a training set according to the noise-free image, the first noise image, and the second noise image.
[0084] It should be noted that a training set can also be constructed according to the second noise image and the noise-free image. In order to obtain more training data, it is preferable to use the noise-free image, the first noise image and the The se...
Embodiment 3
[0088] Embodiment three, see image 3 , the acquisition of the smooth block set of the image to be denoised includes:
[0089] S31. Scan the image to be denoised with a preset step size, and intercept global blocks of a preset size to obtain a global block set.
[0090] In this embodiment, the entire picture of the image to be denoised is scanned with a preset step size sg, and a global block of dxd size is intercepted to obtain a global block set P={p1, p2, ..., pn}, where n greater than or equal to 1.
[0091] S32. Scan each global block in the global block set with a preset step size.
[0092] In this embodiment, each global block P1, p2, ..., pn in the global block set P={p1, p2, ..., pn} is scanned with a preset step size sl.
[0093] S33. Intercepting a local block of a preset size for each global block, so as to obtain a local block set corresponding to each global block.
[0094] In this embodiment, after scanning each global block in the global block set, intercep...
Embodiment 4
[0098] Embodiment four, see Figure 4 , performing noise modeling on the noise block set according to the generative confrontation network, so as to obtain a generator that can generate the same type of noise as the image to be denoised, including:
[0099] S41. Select the generative adversarial network model.
[0100] In this embodiment, any kind of generative adversarial network model, such as WGAN, is selected, which is not specifically limited in the present invention.
[0101] S42. Input random noise into the generator of the GAN model.
[0102] S43. Using the noise block set as a real data sample set, train the generative adversarial network model to obtain a generator capable of generating the same type of noise as the image to be denoised.
[0103] In this embodiment, in order to train and obtain a generator that can generate the same type of noise as the image to be denoised, the noise block set is used as the real data sample set of the discriminant model of the ge...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com