A method for classifying gabor features of hyperspectral images based on incremental local residual least squares
A hyperspectral image and least squares technology, applied in the field of image processing, can solve the problems of huge data volume, insufficient computer memory, affecting the operability of least squares classification, etc., to avoid memory space, reduce data size, and universal good effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0043] This embodiment provides a hyperspectral image Gabor feature classification method based on the incremental local residual least squares method, and adopts the following implementation method:
[0044] (1) Gabor filter feature extraction with given parameters (frequency amplitude and space-spectrum spatial direction) is performed on the hyperspectral image, and the Gabor feature cube of the hyperspectral image under the corresponding parameters is obtained;
[0045] (2) Obtain the pixels marked with specific categories in the hyperspectral image feature cube as training pixels, and the pixels of unmarked categories as test pixels;
[0046] (3) Under the current feature parameters, use the training pixel set to linearly reconstruct the corresponding test pixels, sequentially calculate the reconstructed coefficient matrix and the initial cumulative category local residual between the reconstructed value and the true value of the test pixel, and calculate subsequent updates...
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