Laguerre-Gauss Preprocessing: Line Profiles as Image Features for Aerial Images Classification

TL;DR

This paper introduces a novel preprocessing method using Fourier analysis and Laguerre-Gauss filters to extract compact, informative features from aerial images, enabling effective classification with simpler models.

Contribution

It proposes a new feature extraction technique that reduces feature space size while maintaining classification performance, improving efficiency for aerial image analysis.

Findings

Reduced feature space preserves classification accuracy.

Simple models achieve performance comparable to complex models.

Method effective on challenging aerial image datasets.

Abstract

An image preprocessing methodology based on Fourier analysis together with the Laguerre-Gauss Spatial Filter is proposed. This is an alternative to obtain features from aerial images that reduces the feature space significantly, preserving enough information for classification tasks. Experiments on a challenging data set of aerial images show that it is possible to learn a robust classifier from this transformed and smaller feature space using simple models, with similar performance to the complete feature space and more complex models.