Compressed Sensing Spectral Image Reconstruction Method Based on Sparse Representation of Structural Clustering
A spectral image and sparse representation technology, applied in the field of image processing, which can solve the problems of difficult and high-quality spectral images, and the lack of sparse coefficient correlation information.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0040] refer to figure 1 , the present invention is a compressive sensing spectral image reconstruction method based on structural clustering sparse representation, and its implementation steps are as follows:
[0041] Step 1: Input observation data.
[0042] Input spectral image observation result y∈R h(w+n-1)m and observation matrix H∈R h(w+n-1)m×hwn , where h and w represent the height and width of each spectral segment image respectively, n represents the number of spectra, m represents the number of observations, R represents the real number field, x represents the original spectral image to be solved, x∈R hwn .
[0043] Step 2: Set back projection coefficient δ, sparse coefficient threshold t 1 , maximum iteration step number P, update step size L, spectral image block category number K, image block similarity threshold τ and similarity weight parameter h 0 . The initial recovered spectral image is x (0) =H T y, x (0) ∈R hwn , set the current iteration number p...
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