Image super resolution (SR) reconstruction method based on subspace projection and neighborhood embedding
A technology of super-resolution reconstruction and subspace projection, applied in the field of image processing, which can solve problems such as damage to useful information, slow operation speed, and adverse effects of neighborhood blocks.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0041] An image super-resolution reconstruction method based on subspace projection and neighborhood embedding, comprising the following steps:
[0042] A. Training:
[0043] Take L high-resolution images with the same resolution and the same size as training high-resolution images l=1, 2,..., L, L=3~80; for each training high-resolution image Get N after overlapping blocks 1 training high-resolution image patches of size z*z, N 1 =1000~7000, z=6, 9, 12, 15, get N=L*N altogether 1 training high-resolution image blocks, extracting the standardized luminance feature of each training high-resolution image block as a training high-resolution standardized luminance feature image block, the i-th training high-resolution normalized luminance feature image block by column by column The order of conversion to the i-th training high-resolution feature vector i = 1, 2, ..., N, each training high-resolution feature vector The dimensions are all d 1 =z 2 , all training high-res...
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