Effective subspace detection based on cross cumulative residual entropy for hyperspectral image classification

Remote sensing hyperspectral images are blessings of technology through which the ground objects can be detected effectively with the cost of computer processing. For classification of hyperspectral images finding an effective subspace is very important to classify them efficiently. In recent years, many researchers have drawn their interest to extract data more effectively from hyperspectral dataset. In this research, an approach has been proposed to find the effective subspace by measuring the relevance of individual features through Cross Cumulative Residual Entropy from the Principal Component images. The Support Vector Machine has been used as the classifier for the assessment of the feature reduction performance. Experiment has been completed on real hyperspectral dataset and achieved 97% of accuracy which is better than the standard approaches studied.

I. Introduction

With the advance in technology, imaging sensor has been improved a lot in recent years to capture the greater details of the ground object for effective classification. For instance, the hyper-spectral imaging sensor such as the NASA's Airborne Visible Infrared Imaging Spectrometer (AVIRIS) image sensor can capture 224 bands simultaneously with a spectral resolution of 0.01 [1] in the spectral range of visible to near infrared. The hyper-spectral images can be applied in a number of fields including agriculture, ecology, hydrology, mineralogy etc. Another important use is in land cover classification for the detection of target classes such as the amount of vegetation, built-up areas for the sustainable development of a city etc. These important applications of hyperspectral images create many interests for research now a days [2].