Integrating Global and Local Features of Facial Image in FG-Net Database

Abstract

This paper proposes a novel age estimation method - Global and Local feature based Age estimation (GLAAM) - relying on global and local features of facial images. Global features are obtained with Active Appearance Representations (AAR). Local features are extracted with regional 2D-DCT (2-dimensional Discrete Cosine Transform) of normalized facial images. GLAAM consists of the following modules: face normalization, global feature extraction with AAR, local feature extraction with 2D-DCT, dimensionality reduction by means of Principal Component Analysis (PCA) and age estimation with multiple linear regressions. Experiments have shown that GLAAM outperforms many methods previously applied to the FG-NET database. To integrate the global and local features, a feature level fusion approach is used.