On the usefulness of color for kinship verification from face images

Abstract

Automatic kinship verification from faces aims to determine whether two persons have a biological kin relation or not by comparing their facial attributes. This is a challenging research problem that has recently received lots of attention from the research community. However, most of the proposed methods have mainly focused on analyzing only the luminance (i.e. gray-scale) of the face images, hence discarding the chrominance (i.e. color) information which can be a useful additional cue for verifying kin relationships. This paper investigates for the first time the usefulness of color information in the verification of kinship relationships from facial images. For this purpose, we extract joint color-texture features to encode both the luminance and the chrominance information in the color images. The kinship verification performance using joint color-texture analysis is then compared against counterpart approaches using only gray-scale information. Extensive experiments using different color spaces and texture features are conducted on two benchmark databases. Our results indicate that classifying color images consistently shows superior performance in three different color spaces.