Apparent and real age estimation in still images with deep residual regressors on APPA-REAL database

Eirikur Agustsson (1) , Radu Timofte (1, 2) , Sergio Escalera (3) , Xavier Baró (3) , Isabelle Guyon (4) , Rasmus Rothe (2)

1 D-ITET - Department of Information Technology and Electrical Engineering [Zürich]
2 Merantix GmBH
3 CVC - Computer Vision Center (Centre de visio per computador)
4 TAU - TAckling the Underspecified

After decades of research, the real (biological) age estimation from a single face image reached maturity thanks to the availability of large public face databases and impressive accuracies achieved by recently proposed methods. The estimation of " apparent age " is a related task concerning the age perceived by human observers. Significant advances have been also made in this new research direction with the recent Looking At People challenges. In this paper we make several contributions to age estimation research. (i) We introduce APPA-REAL, a large face image database with both real and apparent age annotations. (ii) We study the relationship between real and apparent age. (iii) We develop a residual age regression method to further improve the performance. (iv) We show that real age estimation can be successfully tackled as an apparent age estimation followed by an apparent to real age residual regression. (v) We graphically reveal the facial regions on which the CNN focuses in order to perform apparent and real age estimation tasks.

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]; Réseau de neurones [cs.NE]

Eirikur Agustsson, Radu Timofte, Sergio Escalera, Xavier Baró, Isabelle Guyon, et al.. Apparent and real age estimation in still images with deep residual regressors on APPA-REAL database. FG 2017 - 12th IEEE International Conference on Automatic Face and Gesture Recognition, May 2017, Washington DC, United States. pp.1-12. ⟨hal-01677892⟩