Feature Selection Parallel Technique for Remotely Sensed Imagery Classification

TL;DR

This paper introduces a parallel feature selection technique for remote sensing image classification that enhances performance on high-dimensional datasets, demonstrating promising results on hyper-spectral and high-resolution images.

Contribution

A novel parallel approach for dependence-based feature selection methods that improves efficiency on large remote sensing datasets.

Findings

Enhanced performance on high-dimensional datasets

Effective feature selection for hyper-spectral images

Promising preliminary results compared to centralized methods

Abstract

Remote sensing research focusing on feature selection has long attracted the attention of the remote sensing community because feature selection is a prerequisite for image processing and various applications. Different feature selection methods have been proposed to improve the classification accuracy. They vary from basic search techniques to clonal selections, and various optimal criteria have been investigated. Recently, methods using dependence-based measures have attracted much attention due to their ability to deal with very high dimensional datasets. However, these methods are based on Cramers V test, which has performance issues with large datasets. In this paper, we propose a parallel approach to improve their performance. We evaluate our approach on hyper-spectral and high spatial resolution images and compare it to the proposed methods with a centralized version as preliminary results. The results are very promising.