Adulthood Classification based on Geometrical Facial Features

Human beings can easily categorize a person’s age group from an image of the person’s face and are often able to be quite precise in this estimation. This ability has not been pursued in the computer vision community. To address this very important area of research, the present paper carried out the task of adulthood classification of a mugshot facial image into a child and adult. The present paper assumes that the features that drastically affect the adulthood classification system are the face geometric properties. Based on this, the present paper proposes a new technique of adulthood classification by extracting feature parameters of face. The feature parameters of the present approach are computed from facial distance features (FDF). From these FDF’s, the various Facial Feature parameters (FFP), and Adulthood Classification Parameters (ACP) are evaluated. The experimental evidence on FGnet aging database and Google Images clearly indicates the significance and accuracy of the proposed classification method.