Performance evaluation for data reduction techniques of hyperspectral images

Abstract

Hyperspectral image contains information as a set of contiguous spectral wavelength bands. These images are three dimensional images having up to two hundred bands or more. Although hyperspectral image contain hundreds of bands, a few number of bands can explain the vast majority of the information. Hence, hyperspectral image is transformed into lower dimension by preserving the main features of the original data using dimension reduction techniques, which eliminate data redundancy. In order to reduce the complexity and the time taken for processing of the hyperspectral images, Principal Component Analysis (PCA) is used to reduce the dimensionality while retaining all important features of the image. In this paper, PCA and Noise Adjusted Principal Component Analysis (NAPCA) have been simulated in the area of hyperspectral image processing. Experiments were carried out on three different types of aerial hyperspectral images having different spectral and spatial resolutions. An elaborate performance evaluation for these data reduction techniques has been carried out by taking image quality parameters such as Peak Signal-to-Noise Ratio (PSNR) and Mean Square Error (MSE). Image quality parameters are calculated using original hyperspectral image and reconstructed images of PCA and NAPCA.