Deep Random Forest for Facial Age Estimation Based on Face Images

The face image of an individual is important for most biometrics systems. The face picture gives loads of helpful informations, including the individual's personal identity, gender, ethnicity, age, emotional expression, and so forth. As of late, a few applications that endeavor age estimation have risen. This paper was aimed to address the problem of image-based human age estimation. It has the following main contributions. We used the advantages of the recent method and algorithms named Gcforest, which proved in several classification tasks, this novel approach includes the power of the decision trees and the advantages of a Cascades structure which allows the interaction between trees. We provide a comparison between two feature types handcrafted and deep feature, we used three databases FG NET, PAL and MORPH II.