AGE ESTIMATION BASED ON FACIAL SHAPE TRANSFORMATION AND CCNNs

The human face is a fundamental part that is used in direct communication and classification; therefore, the Facial Ageing process has been of a good interest to many researchers due to the fact that the face appearance changes as person age resulting in difficulties to identify certain individuals. The ability to synthesize the effects of ageing in individual face has many uses from helping the search for missing people to improving recognition algorithms and aiding surgical planning. In this paper, we aim to extract some facial features and use it for estimating the age of individual using different techniques. The CCNNs have been trained with a set of face features in order to estimate the age of the person in the corresponding face image. We also proposed a facial aging technique that comprises of a shape transformation model aimed to differentiate one‟s appearance across ages. In addition, we have asked a number of volunteers to estimate the age of people in the typical sample of face images so we could compare the performance of our age estimator against the performance of humans. Our results indicate that machines can estimate the age of a person almost as reliably as humans.