Efficient Depth Features for Age-Group Classification

Age estimation has lots of real-world applications, such as security control, biometrics, customer relationship management, entertainment and cosmetology. In fact, Face-based age estimation has gained wide popularity in recent years. Despite numerous research efforts and advances in the last decade, traditional human age-group recognition with the sequence of 2D colour images is still a challenging problem. Thus, the goal of this work is to recognize human age-group only using depth maps without additional joints information. As a practical solution, we present a novel representation of global appearance of aging effect such as wrinkles’ depth. The proposed framework relay, first-of-all, on an extended version of Viola-Jones algorithm for face and region of interest (most affected by aging) extraction. Then, two depth descriptors are proposed in order to extract efficient age characterization and track aging effect evolutions. These descriptors mean to compute the depth variances from the interest face’s regions in the first time and track the 3D gradients orientation on these regions. Such features describe local appearances and shapes of the depth map, for more compact and discriminative aging effect representation. Experimental study performed on large 3D databases integrating age-group variations proves the performances of using depth features to enhance previous age estimation results. The presented methods have been also, compared with the state-of-the-art 2D-approaches. Results demonstrate that our descriptors achieve better and more stable performances.