Band selection and classification of hyperspectral images by minimizing normalized mutual information

TL;DR

This paper proposes a fast, effective feature selection method for hyperspectral image classification using normalized mutual information to reduce redundancy and improve accuracy.

Contribution

It introduces a novel feature selection scheme based on normalized mutual information to control redundancy in hyperspectral image classification.

Findings

Effective reduction of redundant bands

Improved classification accuracy

Fast feature selection process

Abstract

Hyperspectral images (HSI) classification is a high technical remote sensing tool. The main goal is to classify the point of a region. The HIS contains more than a hundred bidirectional measures, called bands (or simply images), of the same region called Ground Truth Map (GT). Unfortunately, some bands contain redundant information, others are affected by the noise, and the high dimensionalities of features make the accuracy of classification lower. All these bands can be important for some applications, but for the classification a small subset of these is relevant. In this paper we use mutual information (MI) to select the relevant bands; and the Normalized Mutual Information coefficient to avoid and control redundant ones. This is a feature selection scheme and a Filter strategy. We establish this study on HSI AVIRIS 92AV3C. This is effectiveness, and fast scheme to control redundancy. Index Terms: Hyperspectral images, Classification, Feature Selection, Normalized Mutual Information, Redundancy.