Date of Publication :5th January 2018

Abstract: In this paper, an innovative approach age estimation method based on decision level fusion of global and local characteristics is proposed. The structure and occurrence knowledge of human faces which are extracted with active appearance representations (AAR) are used as global facial characteristics. The local facial characteristics are the wrinkle characteristics extracted with Gabor filters and skin characteristics extracted with local binary patterns (LBP). Then facial characteristic classification is performed using an Innovative classifier which is the combination of an age group classification and specific age estimation. In the age group classification level, three distinct support vector machines (SVM) classifiers are trained using each characteristic vector. Then decision level fusion is performed to combine the results of these classifiers. The specific age of the classified image is then estimated in that age group, using the aging functions modeled with global and local characteristics, separately. Aging functions are modeled with multiple linear regressions. To make a final decision, the results of these aging functions are also fused in decision level.

Reference :