Facial Age Group Classification

Abstract

Estimating human age group automatically via facial image analysis has lots of potential real-world applications, such as human computer interaction and multimedia communication. However, It is still a challenging problem for the existing computer vision systems to automatically and effectively estimate human age group. The aging process is determined by not only the person's gene, but also many external factors, such as health, living style, living location, and weather conditions. Males and females may also age differently. An age group classification system for facial images is proposed in this paper. Five age groups including babies, children, young adults, middle-aged adults, and old adults, are used in the classification system. The process of the system is divided into threephases: location, feature extraction, and age classification. Geometric features are used to distinguish whether the face is baby or child. Wrinkle features are used to classify the image into one of three adult groups-young adults, middle-aged adults, and old adults.