Age Group Estimation Using Face Angle

Abstract

Recognition of the most facial variations, such as identity, expression and gender, has been extensively studied. Automatic age estimation has rarely been explored. With age progression of a human the face angle changes. This paper concerns with providing a methodology to estimate age groups using face features. The proposed method is based on the face triangle which has three coordinate points between left eye ball, right eyeball and mouth point. The face angle between left eyeball, mouth point and right eyeball estimates the age of a human. However, very few studies have been done on age classification or age estimation. This paper proves that face angle can estimate and classify human age according to face features extracted from human facial images. Age ranges are classified into five categories. Those are child (up to 17 years), young (18 to 25 years), adult (26 to 35 years), middle aged (36 to 45 years) and old (more than 45 years). The obtained results were significant. This paper can be used for predicting future faces, classifying gender, and expressions from facial images.