HUMAN AGE CLASSIFICATION WITH OPTIMAL GEOMETRIC RATIOS AND WRINKLE ANALYSIS

Abstract

This paper presents geometric feature-based model for age group classification of facial images. The feature extraction is performed considering significance of the effects that age has on facial anthropometry. Particle Swarm Optimization (PSO) technique is used to find optimized subset of geometric features. The relevance and importance of age differentiation capability of the features are evaluated using support vector classifier. The facial images are categorized in seven major age groups. The effectiveness and accuracy of the proposed feature extraction is demonstrated with the experiments that are conducted on two publicly available databases namely Face and Gesture Recognition Research Network (FGNET) Aging Database and Iranian Face Database (IFDB). The results demonstrate that the success rate of the classification is 92.62%. The results also show significant improvement compared to the state-of-the-art models.