Single image super-resolution method based on identical scale structure self-similarity and compressed sensing
A technology of structural self-similarity and compressed sensing, applied in the field of super-resolution, can solve the problems that the effect of high-resolution reconstructed images cannot be guaranteed, the efficiency of dictionary learning cannot be guaranteed, and the computing efficiency is not high, so as to achieve a good reconstruction effect, The effect of low computational complexity and guaranteed computational efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0025] The present invention will be further described in detail below in conjunction with the drawings and embodiments.
[0026] As shown in the figure, a single-image super-resolution method based on self-similarity and compressed sensing of the same-scale structure includes the following steps:
[0027] Step 1: Perform bicubic interpolation on the low-resolution image Y to obtain the quasi-high-resolution image X′;
[0028] Step 2: Divide the quasi-high-resolution image X′ into 4×4 quasi-high-resolution image blocks, and each quasi-high-resolution image block corresponds to a vector x′ i , There can be a certain overlap between the quasi-high resolution image blocks;
[0029] Step 3: Convert the obtained vector x′ i As a training sample and form a sample matrix S=[x′ 1 ,..., x′ s ], use the K-SVD dictionary learning method to solve the following formula to obtain the dictionary ψ;
[0030] min Ψ , A { | | S - ΨA | | F 2 } subject to ∀ i ...
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