Unconstrained Age Estimation With Deep Convolutional Neural Networks

We propose an approach for age estimation from unconstrained images based on deep convolutional neural networks (DCNN). Our method consists of four steps: face detection, face alignment, DCNN-based feature extraction and neural network regression for age estimation. The proposed approach exploits two insights: (1) Features obtained from DCNN trained for face-identification task can be used for age estimation. (2) The three-layer neural network regression method trained on Gaussian loss performs better than traditional regression methods for apparent age estimation. Our method is evaluated on the apparent age estimation challenge developed for the ICCV 2015 ChaLearn Looking at People Challenge for which it achieves the error of 0:373.