Band selection and classification of hyperspectral images by minimizing normalized mutual information
This work addresses the issue of high dimensionality and redundancy in hyperspectral images for remote sensing classification, though it appears incremental as it applies an existing method to a specific dataset.
The paper tackles the problem of redundant and noisy bands in hyperspectral image classification by using mutual information for band selection and normalized mutual information to control redundancy, resulting in an effective and fast scheme tested on the AVIRIS 92AV3C dataset.
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.