Age Estimation Based on ECG and Combined Features from Randomized Facial Blocks

This paper proposed a novel method to improve automatic age estimation from human faces. Three types of feature extraction algorithms are used, such as Extended Curvature Gabor Filter (ECG), Completed Local Binary Pattern (CLBP), and Local Directional Pattern (LDP). While the ECG is applied to the entire human face, CLBP and LDP are only applied to blocks with randomized scales, positions and orientations. Then, Support Vector Machine is used to estimate the age from combined feature histograms. The Mean Absolute Error of the proposed method is 4.49 years old, which is better than existing methods.