Feature extraction of hyperspectral image using principal component analysis and folded-principal component analysis

Hyperspectral imaging is one of the advanced remote sensing techniques. High dimensional nature of hyperspectral image makes its analysis complex. Various methods have been developed to reduce the dimension of hyperspectral image. Most commonly used dimension reduction technique is Principal Component Analysis (PCA), which is a feature extraction method. The main shortcoming of PCA method is that it does not consider the local structures. Folded-PCA (F-PCA) takes into account both global and local structures, while preserving all useful properties of PCA. This paper presents comparative study of PCA and Folded-PCA approach for feature extraction of hyperspectral image.

I. Introduction

Hyperspectral Imaging (HSI) is a foremost research area in Remote Sensing. Our eyes only see visible band of the light spectrum. Many more bands of non-visible light exist to the left and right of visible spectrum. Hyperspectral Imaging is a technology which divides regions of those spectra which we can't see into many more bands and creates visible images from them. This is known as the Electromagnetic Spectrum. Thus HSI captures data in numerous continuous spectral bands and forms hyperspectral data cube. The structure of hyperspectral image cube is depicted in Fig. 1. Figure 1.

Hyperspectral image cube