Local and global features fusion to estimate expression invariant human age

Abstract

Human beings can easily estimate the age or age group of a person from a facial image where as this capability is not prominent in machines. This problem becomes more complex due to presence of different facial expressions and age progression. In this paper, we introduced a novel method for age prediction using combination of local and global features. After detecting the face from image, we partition the facial image in 16 * 16 non-overlapping blocks and apply grey-level co-occurrence matrix (GLCM) on these blocks. After calculating four facial parts (eyes, forehead, left cheek and right cheek) from facial image, features from second local feature Gabor filter are obtained. Histogram of oriented gradients has been used as a global feature for feature extraction from complete face image. Experimental results show that fusion of local and global features perform better than existing approaches and reported 6.31 years mean absolute error (MAE) on PAL dataset.