Human age estimation framework using different facial parts

Abstract

Human age estimation from facial images has a wide range of real-world applications in human computer interaction (HCI). In this paper, we use the bio-inspired features (BIF) to analyze different facial parts: (a) eye wrinkles, (b) whole internal face (without forehead area) and (c) whole face (with forehead area) using different feature shape points. The analysis shows that eye wrinkles which cover 30% of the facial area contain the most important aging features compared to internal face and whole face. Furthermore, more extensive experiments are made on FG-NET database by increasing the number of missing pictures in older age groups using MORPH database to enhance the results.

Keywords

• Age estimation
• Bio-inspired features
• Support vector machine
• Support vector regression