A Hierarchical System for Age Estimation Based on Appearance Feature and Ranking-KNN

Author

Yuyu Liang ; Xianmei Wang ; Li Zhang ; Zhiliang Wang

Author_Institution

Univ. of Sci. & Technol., Beijing, China

fYear

2013

fDate

6-7 Nov. 2013

Firstpage

1

Lastpage

4

Abstract

Age estimation is a complex issue of multi-classification or regression. To address a common problem of uneven distribution of age database, this paper shows a hierarchic age estimation system, comprising age group and specific age estimation. In our system, two novel classifiers, Sequence K-Nearest Neighbor (SKNN) and Ranking-KNN, are introduced to predict age group and age value respectively. Notably, Ranking-KNN utilizes the ordinal information between samples in estimation process rather than regards samples as separate individuals. Tested on FG-NET database, our system achieves 5.37 evaluated by MAE (Mean Absolute Error) for age estimation. And the comparison between our solution and others is also shown.

Keywords

age issues; database management systems; regression analysis; FG-NET database; MAE; age group; age value; appearance feature; hierarchic age estimation system; mean absolute error; multiclassification; ranking-KNN; regression analysis; sequence k-nearest neighbor; specific age estimation; Accuracy; Classification algorithms; Databases; Estimation; Face; Feature extraction; Testing; Information Domain; Integrated System; Intelligent Building; ezIBS;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems Design and Engineering Applications, 2013 Fourth International Conference on

Conference_Location

Zhangjiajie

Print_ISBN

978-1-4799-2791-3

Type

conf

DOI

10.1109/ISDEA.2013.406

Filename

6843383