Albedo recovery for hyperspectral image classification
| Autor: | Haibo Wang, Kun Zhan, Yufang Min, Chutong Zhang, Yuange Xie |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Generalization
business.industry Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 0211 other engineering and technologies Hyperspectral imaging Pattern recognition 02 engineering and technology Albedo Atomic and Molecular Physics and Optics Computer Science Applications Image (mathematics) Albedo feature Support vector machine Margin (machine learning) Component (UML) 0202 electrical engineering electronic engineering information engineering Artificial Intelligence & Image Processing 020201 artificial intelligence & image processing Computer vision Artificial intelligence Electrical and Electronic Engineering business ComputingMethodologies_COMPUTERGRAPHICS 021101 geological & geomatics engineering |
| Zdroj: | Journal of Electronic Imaging. 26:043010 |
| ISSN: | 1017-9909 |
| DOI: | 10.1117/1.jei.26.4.043010 |
| Popis: | © 2017 SPIE and IS & T. Image intensity value is determined by both the albedo component and the shading component. The albedo component describes the physical nature of different objects at the surface of the earth, and land-cover classes are different from each other because of their intrinsic physical materials. We, therefore, recover the intrinsic albedo feature of the hyperspectral image to exploit the spatial semantic information. Then, we use the support vector machine (SVM) to classify the recovered intrinsic albedo hyperspectral image. The SVM tries to maximize the minimum margin to achieve good generalization performance. Experimental results show that the SVM with the intrinsic albedo feature method achieves a better classification performance than the state-of-the-art methods in terms of visual quality and three quantitative metrics. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|