Classification of Age Groups from Facial ImageUsing Histograms of Oriented Gradients

In this paper, we propose an age-group classificationalgorithm using Histograms of Oriented Gradients (HOG) as theface description. The proposed method classifies subjects intofour different age groups. The process of the system is dividedinto three main stages: pre-processing, feature extraction andage-group classification. In this work, we use Iranian FaceDatabase (IFDB) [1] since the actual age of the subjects aredetermined in this database. IFDB contains the images of thesubjects with age span from 1 to 85 years. After pre-processing,HOG features of the faces are extracted and then, the images areclassified into age-groups using a PNN classifier. Experimentalresults show that recognition rate of the proposed method is87.025% for age-group classification.

Keywords:

age-group classification , facial feature extraction , histograms of oriented gradients