MA Chuang1, TIAN Qing1,2*, SUN Heyang1, CAO Meng1
(1 School of Computer and Software, Nanjing University of Information Science & Technology, Nanjing 210044, Jiangsu, China;2 Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, Jiangsu, China)
Abstract:
Human age estimation has attracted increasing research due to its wide applicability.Although a variety of methods have been proposed, most of them only focus on the age-specific facial appearance and the aging difference between the male and the female inevitably affect the age estimation.A unified framework to perform gender-aware age estimation is proposed. The proposed method considers and utilizes the semantic relationship between the gender and the age, sand the aging discrepancy between the male and the female. Finally, experimental results demonstrate not only the superiority of our method in performance, but also its good interpretability in revealing the aging discrepancy.
KeyWords:
age estimation; gender-aware age estimation; threshold-based ordinal regression; support vector ordinal regression
