Age Classification in Unconstrained Conditions Using LBP Variants
Juha Ylioinas, Abdenour Hadid · 2016
Automatic age classification from human faces is a challenging task which has recently attained an increas-ing attention. Most of the proposed approaches have however been mainly dealing with controlled settings. In this paper, we propose a novel method for age clas-sification in unconstrained conditions and provide ex-tensive performance evaluation on benchmark datasets with standard protocols, thus allowing a fair compar-ison and an easy reproduction of the results. Our pro-posed method is based on a combination of local binary pattern (LBP) variants encoding the structure of elon-gated facial micro-patterns and their strength. The ex-perimental analysis points out the complexity of the age classification problem under uncontrolled settings. The proposed method provides state-of-the-art performance that can be used as a reference for future investigations. 1.