Image Processing and Recognition - Mixture of Experts for Classification of Gender, Ethnic Origin, and Pose of Human Faces

Published

July 1, 2000

Author(s)

S Gutta, J Huang, P. Jonathon Phillips, H Wechsler

Abstract

In this paper we describe the application of mixtures of experts on gender and ethnic classification of human faces, and pose classification, and show their feasibility on the FERET database of facial images. The FERET database allows us to demonstrate performance on hundreds or thousands of images. The mixture of experts is implemented using the divide and conquer modularity principle with respect to the granularity and/or the locality of information. The mixture of experts consists of an ensembles of radial basis functions (RBF). Inductive decision trees (DT) and support vector machines (SVM) implement the gating network components for deciding which of the experts should be used to determine the classification output and to restrict the support of the input space. Both the Ensemble of RBFs (ERBF) and SVM use the RBF kernel (expert) for gating the inputs. Our experimental results yield an average accuracy rate of 96 % on gender classification and 92 % on ethnic classification using the ERBF / DT approach from frontal face images, while the SVM yield 100 % on pose classification.

Proceedings Title

IEEE Transactions on Neural Networks | | | IEEE

Conference Dates

July 1, 2000

Conference Location

Undefined

Conference Title

IEEE Transactions on Neural Networks

Pub Type

Conferences

Keywords

decision trees, face processing, neural networks

Citation

Gutta, S. , Huang, J. , Phillips, P. and Wechsler, H. (2000), Image Processing and Recognition - Mixture of Experts for Classification of Gender, Ethnic Origin, and Pose of Human Faces, IEEE Transactions on Neural Networks | | | IEEE, Undefined (Accessed July 17, 2024)