Automatic Age Estimation And Gender Classification In The Wild
Résumé
Automatic age estimation and gender classification throughfacial images are attractive topics in computer vision. Theycan be used in many real-life applications such as face recog-nition and internet safety for minors. In this paper, we presenta novel approach for age estimation and gender classificationunder uncontrolled conditions following the standard proto-cols for fair comparaison. Our proposed approach is based onMulti Level Local Binary Pattern (ML-LBP) features whichare extracted from normalized face images. Two differentSupport Vector Machines (SVM) models are used to predictthe age group and the gender of a person. The experimen-tal results on benchmark Image of Groups dataset showed thesuperiority of our approach compared to that of the state-of-the-art methods