Hyperspectral image classification method based on affinity propagation clustering and sparse multiple kernel learning
A hyperspectral image and hyperspectral classification technology, which is applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of difficult hyperspectral image data processing, high computational complexity of multi-core learning methods, and large kernel scale. Achieve the effect of overcoming the high time complexity, avoiding the degradation of classification performance, and broad application prospects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0030] refer to figure 1 , the implementation steps of the present invention are as follows:
[0031] Step 1, input a hyperspectral image, obtain training samples and test samples.
[0032] (1.1) Input hyperspectral image: The image contains l spectral bands and n samples;
[0033] (1.2) Randomly select 10% samples from these n samples to form a training sample set Use the remaining samples to form the test sample set Among them, pp and qq respectively represent the number of training samples and testing samples, satisfying pp+qq=n.
[0034] Step 2, for the training sample set X pp and the test sample set X qq Perform column normalization operations respectively to obtain the training sample set X after column normalization p and the test sample set X q .
[0035] Step 3, use the normalized training sample set X p In the l bands, the Gaussian kernel matrix set K is constructed through m different kernel parameters.
[0036] (3.1) Extract training sample set X p Th...
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