On the usefulness of color for kinship verification from face images

摘要: 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 challenging research problem that has recently received lots of attention the community. However, most proposed methods mainly focused on analyzing only luminance (i.e. gray-scale) face images, hence discarding chrominance color) information which can be useful additional cue for verifying relationships. paper investigates first time usefulness color in relationships images. For this purpose, we extract joint color-texture features encode both and The performance using analysis then compared against counterpart approaches gray-scale information. Extensive experiments different spaces texture are conducted benchmark databases. Our results indicate classifying images consistently shows superior three spaces.