Facial age estimation using artificial neural network and robust feature extraction

Abstract

Aging is the process of changing the status of human body which human face shows the most important changes. One of the most challenges of age estimation methods is feature extraction which the feature extraction method is failed to extract full informative feature vector elements in the case of deformation, scaling,… in image. So, a feature extractor which is robust against to the situations is necessary. This paper proposes a new method of age estimation where Pseudo Zernike Moment (PZM). The task of age prediction in the proposed method is performed using Artificial Neural Network (ANN) with the type of Multi-Layer Perceptron. The proposed method is evaluated on FG-NET dataset and the results prove the ability of the proposed method .