Automatial Facial Age Estimation

Abstract— Estimating human age from images is a problem that has recently gained attention from the computer vision community due to its numerous applications as well as the challenges that face a satisfactory solution. Beside traditional challenges in captured facial images under uncontrolled settings such as different lighting, varying poses and expressions, aging effects on appearance depends on many other factors such as life style. In this thesis, a new automatic age estimation framework is proposed. A single image is required as input for the subject of interest to estimate his age. The framework is composed of three main modules: 1) the core system module; 2) the enhancement module; and 3) the application module. The core system module comprises the main blocks of image representation and learning for age estimation. For age image representation, a novel technique is introduced for capturing different aging features using an extension of the popular biologically inspired features (BIF). Several enhancements are considered for improving the performance of BIF such as encoding micro facial features. On the learning side, an ensemble of support vector classifiers and regressors is combined yielding to results surpassing the state-of-the art on standard datasets. The proposed method can estimate ages ranging from 0 to 80 with as little average absolute error as three years. < final year projects >