Implementation of neural network operators with applications to remote sensing data

TL;DR

This paper introduces two neural network operator algorithms for modeling and enhancing remote sensing images, demonstrating superior performance over classical methods like bilinear and bicubic interpolation in SSIM metrics.

Contribution

The paper develops and applies two multidimensional neural network algorithms for remote sensing data modeling and enhancement, backed by theoretical justification and numerical experiments.

Findings

Algorithms outperform classical interpolation methods in SSIM.

Neural network operators effectively model and enhance remote sensing images.

Theoretical results support the algorithms' performance.

Abstract

In this paper, we provide two algorithms based on the theory of multidimensional neural network (NN) operators activated by hyperbolic tangent sigmoidal functions. Theoretical results are recalled to justify the performance of the here implemented algorithms. Specifically, the first algorithm models multidimensional signals (such as digital images), while the second one addresses the problem of rescaling and enhancement of the considered data. We discuss several applications of the NN-based algorithms for modeling and rescaling/enhancement remote sensing data (represented as images), with numerical experiments conducted on a selection of remote sensing (RS) images from the (open access) RETINA dataset. A comparison with classical interpolation methods, such as bilinear and bicubic interpolation, shows that the proposed algorithms outperform the others, particularly in terms of the Structural Similarity Index (SSIM).