Determination of the most representative descriptor among a set of feature vectors for the same object

TL;DR

This paper proposes a method to identify the most representative feature descriptor for an object, specifically faces, by robustly estimating a mode-median mixture vector using a loss function suitable for sparse data.

Contribution

It introduces a novel approach for selecting the most representative descriptor among multiple feature vectors using robust statistical estimation with Welsch/Leclerc loss.

Findings

Effective in sparse feature space scenarios

Robust estimation improves descriptor selection accuracy

Applicable to face recognition tasks

Abstract

On an example of solution of the face recognition problem the approach for estimation of the most representative descriptor among a set of feature vectors for the same face is considered in present study. The estimation is based on robust calculation of the mode-median mixture vector for the set as the descriptor by means of Welsch/Leclerc loss function application in case of very sparse filling of the feature space with feature vectors