A design of gender and age estimation system based on facial knowledge

The purpose of this paper is to propose a method of gender and age estimation which is robust for environmental changing. We propose a feature-point detection method which is the Advanced Retinal Sampling Method (ARSM), and a feature extraction method. As features for the gender and age estimation, facial shape, skin texture, hue and Gabor-feature are used. In order to show the effectiveness of proposed method, not only real-age database of facial image but also appearance-age database is employed. We also analyze the facial features characteristic to each age category and gender, and examine the difference feature of between the real-age and appearance-age in a facial area. Moreover, we examined the left-right symmetric property of the face concerning gender and age estimation by the proposed method.