Facial age estimation using Zernike Moments and multi-layer perceptron
Mohsen Eshghan Malek, Zohreh Azimifar, Reza Boostani · 2017
Face image of a human contains significant information in terms of gender, facial emotion, race, age and identity. Among these features, the age factor changes over the lifetime and highly affects the human face appearance. This paper proposes a new age estimation system to estimate the age of a human by his/her image. In the proposed method, Zernike Moments (ZM) are utilized for the first time and the extracted features of each face is applied to three classifiers including K-Nearest Neighbor (KNN), Support Vector Regression (SVR) and Multi-Layer Perceptron (MLP) neural network. The proposed algorithm along with state-of-the-art methods were evaluated on the FG-NET dataset. The results imply the proposed features along with MLP outperform the conventional schemes on this dataset.