Human expert fusion for image classification

TL;DR

This paper introduces models for fusing multiple human expert opinions in image classification tasks, accounting for uncertainty and mixed class presence within image tiles, using Dempster-Shafer and Dezert-Smarandache theories.

Contribution

It proposes five novel models for expert opinion fusion in image classification, incorporating uncertainty and mixed class information using advanced belief theories.

Findings

Models effectively handle uncertain expert opinions

Fusion improves classification decision reliability

Theoretical analysis of decision possibilities

Abstract

In image classification, merging the opinion of several human experts is very important for different tasks such as the evaluation or the training. Indeed, the ground truth is rarely known before the scene imaging. We propose here different models in order to fuse the informations given by two or more experts. The considered unit for the classification, a small tile of the image, can contain one or more kind of the considered classes given by the experts. A second problem that we have to take into account, is the amount of certainty of the expert has for each pixel of the tile. In order to solve these problems we define five models in the context of the Dempster-Shafer Theory and in the context of the Dezert-Smarandache Theory and we study the possible decisions with these models.