Automated clustering and estimation of age groups from face images using the local binary pattern operator

Automated age estimation from facial images has recently drawn a lot of attention from the research community emerging as a key technology with numerous applications ranging from access control to human machine interaction. In this research study, we explore a vision-based approach for the estimation of age groups from face images. The local binary pattern operator is applied to derive a set of hybrid features composed local and global characteristics from the face. A histogram of features is constructed based on the concatenation of locally produced histogram vectors from grid cells of face images. Hierarchical feature selection is described for the classification process where age ranges determined automatically in a tree-based fashion. Feature selection is based on the proximity of instances belonging to the same range is applied to obtain the most discriminative traits at each level of the defined age range. Experimental results carried out on a publicly available dataset confirmed the efficiency for the method to better cluster and estimate different age groups for different face images.