Belief decision support and reject for textured images characterization

TL;DR

This paper introduces a belief decision model for textured image classification that allows rejecting uncertain areas and combining classes, demonstrated through seabed characterization from sonar images.

Contribution

It presents a novel belief decision framework enabling rejection of unlearned classes and handling multiple textures within classification units.

Findings

Effective rejection of unlearned classes in textured images

Ability to decide on unions and intersections of classes

Application to seabed characterization from sonar images

Abstract

The textured images' classification assumes to consider the images in terms of area with the same texture. In uncertain environment, it could be better to take an imprecise decision or to reject the area corresponding to an unlearning class. Moreover, on the areas that are the classification units, we can have more than one texture. These considerations allows us to develop a belief decision model permitting to reject an area as unlearning and to decide on unions and intersections of learning classes. The proposed approach finds all its justification in an application of seabed characterization from sonar images, which contributes to an illustration.