The Community for Technology Leaders
2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
ISBN: 978-1-4244-2339-2
pp: 1-6
Charles R. Dyer , Computer Sciences, UW-Madison, WI, 53706 USA
Thomas S. Huang , Beckman Institute, UIUC, Urbana, IL 61801 USA
Yun Fu , Beckman Institute, UIUC, Urbana, IL 61801 USA
Guodong Guo , Computer Science, NCCU, Durham, NC, 27707 USA
ABSTRACT
Human age prediction is useful for many applications. The age information could be used as a kind of semantic knowledge for multimedia content analysis and understanding. In this paper we propose a Probabilistic Fusion Approach (PFA) that produces a high performance estimator for human age prediction. The PFA framework fuses a regressor and a classifier. We derive the predictor based on Bayes’ rule without the mutual independence assumption that is very common for traditional classifier combination methods. Using a sequential fusion strategy, the predictor reduces age estimation errors significantly. Experiments on the large UIUC-IFP-Y aging database and the FG-NET aging database show the merit of the proposed approach to human age prediction.
INDEX TERMS
CITATION
Charles R. Dyer, Thomas S. Huang, Yun Fu, Guodong Guo, "A Probabilistic Fusion Approach to human age prediction", 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 00, no. , pp. 1-6, 2008, doi:10.1109/CVPRW.2008.4563041
98 ms
(Ver )