Abstract
Making a high dimensional (e.g., 100k-dim) feature for hyperspectral image classification seems not a good idea because it will bring difficulties on consequent training, computation, and storage. In this paper, we study the performance of a high-dimensional feature by texture feature. The texture feature based on multi-local binary pattern descriptor, can achieve significant improvements over both its tradition version and the one we proposed in our previous work. We also make the high-dimensional feature practical, we employ the PCA method for dimension reduction and support vector machine for hyperspectral image classification. The two real hyperspectral image datasets are employed. Our experimental results with real hyperspectral images indicate that the high dimensional feature can enhance the classification accuracy than some low dimensional.
Highlights
Hyperspectral image (HSI) captures reflectance values from Visible to Infrared spectrum which cover the wide spectral range with hundreds of bands for each pixel in the image
The first data was collected by Airborne Visible/Infrared Image Spectrometer (AVIRIS) over Northwest Indiana, Indiana, USA, in June 1992
We have investigate that the high dimensional feature is good for HSI classification
Summary
Hyperspectral image (HSI) captures reflectance values from Visible to Infrared spectrum which cover the wide spectral range with hundreds of bands for each pixel in the image. This rich spectral information provides possibility to distinguish different materials spectrally. Local binary pattern operator, which extract texture feature in spatial domain, is used in HSI for classification[ iii ]. Different local size can provide the different features. High-dimensional feature leads to high cost while displays more information for classification. We first extend texture feature based on multi-local binary pattern descriptor in spectrum domain. We make the high-dimensional feature practical, we employ the PCA method for
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have