Classification of Age Groups from Facial Image Using Histograms of Oriented Gradients

In this paper, we propose an age-group classification algorithm using Histograms of Oriented Gradients (HOG) as the face description. The proposed method classifies subjects into four different age groups. The process of the system is divided into three main stages: pre-processing, feature extraction and age-group classification. In this work, we use Iranian Face Database (IFDB) [1] since the actual age of the subjects are determined in this database. IFDB contains the images of the subjects with age span from 1 to 85 years. After pre-processing, HOG features of the faces are extracted and then, the images are classified into age-groups using a PNN classifier. Experimental results show that recognition rate of the proposed method is 87.025% for age-group classification.