Method for lossy compression of hyperspectral image based on classified DCT (discrete cosine transform)
A discrete cosine transform, hyperspectral image technology, applied in the field of image processing, can solve the problem of inaccurate spectral vector classification, and achieve the effect of strong correlation, improved accuracy, and small spectral vector residual error.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0018] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0019] refer to figure 1 , the implementation steps of the present invention are as follows:
[0020] Step 1, input hyperspectral image.
[0021] Input a hyperspectral image {W with the total number of spectral segments Y, width W, and height H 1 ,W 2 ,...,W y ,...,W Y}, where W y ={I 1,1,y , I 1,2,y ,...,I i,j,y ,...,I H,W,y} represents the image of the yth spectral segment, I i,j,y Represents the real pixel gray value of the yth spectral segment, the ith row, and the jth column in the hyperspectral image, i=1,2,...,H,j=1,2,...,W,y=1,2, ..., Y;
[0022] Step 2, group the input hyperspectral images.
[0023] The input hyperspectral image {W 1 ,W 2 ,...,W k ,...,W Y} are equally divided into N groups, and the grouped hyperspectral images are obtained, and each group uses {W 1 ,W 2 ,...,W k ,...,W P} means, denoted as where W k ={I 1,1,...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap