Fusion for Evaluation of Image Classification in Uncertain Environments

TL;DR

This paper introduces a novel evaluation method that simultaneously assesses classification and segmentation of textured images in uncertain environments, incorporating expert certainty, demonstrated on sonar seabed data.

Contribution

It proposes a new combined evaluation approach for classification and segmentation considering expert certainty, filling a gap where these are usually assessed separately.

Findings

Effective fusion of classifiers improves seabed characterization.

The method accounts for partial certainty in expert annotations.

Results show enhanced evaluation accuracy in uncertain environments.

Abstract

We present in this article a new evaluation method for classification and segmentation of textured images in uncertain environments. In uncertain environments, real classes and boundaries are known with only a partial certainty given by the experts. Most of the time, in many presented papers, only classification or only segmentation are considered and evaluated. Here, we propose to take into account both the classification and segmentation results according to the certainty given by the experts. We present the results of this method on a fusion of classifiers of sonar images for a seabed characterization.