Title :
How Do Facial Expressions Contribute to Age Prediction?
Author :
Yingmei Piao ; Kudo, Motoi
Author_Institution :
Grad. Sch. of Inf. Sci. & Technol., Hokkaido Univ., Sapporo, Japan
Abstract :
Human age estimation based on facial images has many potential applications in practice. However, the current age estimation techniques are not matured. Most studies focus only on neutral faces, that is, expressionless faces. Several expressions such as happy expression, may help to improve the prediction accuracy. Recently, some works reported that expressions could badly impact on the accuracy. In this paper, we investigated the degree of facial expression impact on age prediction subjectively and objectively. It was revealed that expressions do not contribute for age prediction so much.
Keywords :
emotion recognition; estimation theory; face recognition; age prediction; facial expression; facial image; happy expression; human age estimation; Aging; Databases; Estimation; Feature extraction; Kernel; Support vector machines; Training; age prediction; facial expresison;
Conference_Titel :
Pattern Recognition (ACPR), 2013 2nd IAPR Asian Conference on
Conference_Location :
Naha
DOI :
10.1109/ACPR.2013.161