Histogram based automatic noisy band removal for remotely sensed hyperspectral images

Abstract

For accurate classification of remote sensing data, Hyperspectral Images (HSI) have become very popular. It can capture the reflected electromagnetic spectrum from the object in several contiguous spectral bands. But processing of hundreds of bands is computationally expensive and also it contains several noisy and redundant bands. Often the water absorption bands are manually removed by the researchers in advance. In this work, a histogram based automatic noisy band removal algorithm is developed for the HSI. This algorithm can be used as a preprocessing step prior to hyperspectral image classification. At first, by using the histogram information, noisy bands are removed. Next, after obtaining the desired number of non-noisy bands, a Gaussian Filter is applied on obtained bands to extract spatial-spectral features. Finally, to evaluate the algorithm, classification is performed using a SVM classifier. For experimental validation of results, Indian Pines and Salinas datasets are used. The obtained result clearly reveals the effectiveness of the proposed automatic noisy band removal algorithm.