View-based eigenspaces with mixture of experts for view-independent face recognition

Authors:
Reza Ebrahimpour;Ehsanollah Kabir;Mohammad Reza Yousefi
Affiliations:
School of Cognitive Sciences, Institute for Studies on Theoretical Physics and Mathematics, Niavaran, Tehran, Iran and Department of Electrical Engineering, Shahid Rajaee University, Tehran, Iran;Department of Electrical Engineering, Tarbiat Modarres University, Tehran, Iran;Department of Electrical Engineering, Shahid Rajaee University, Tehran, Iran
Venue:
MCS'07 Proceedings of the 7th international conference on Multiple classifier systems
Year:
2007

Citing 12
Cited 1

Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces

IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual learning and recognition of 3-D objects from appearance

International Journal of Computer Vision
Face Recognition by Elastic Bunch Graph Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Meta-Analysis of Face Recognition Algorithms

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Face Recognition Under Varying Pose

Face Recognition Under Varying Pose
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
Face recognition from a single image per person: A survey

Pattern Recognition
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Adaptive mixtures of local experts

Neural Computation
A survey of approaches and challenges in 3D and multi-modal 3D+2D face recognition

Computer Vision and Image Understanding

Teacher-directed learning in view-independent face recognition with mixture of experts using overlapping eigenspaces

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.01

Visualization

Abstract

We propose a new model for view-independent face recognition, which lies under the category of multi-view approaches. We use the so-called "mixture of experts", ME, in which, the problem space is divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In the proposed model, instead of allowing ME to partition the face space automatically, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. In this model, view-dependent representations are used to direct the experts towards a specific area of face space. The experimental results support our claim that directing the mixture of experts to a predetermined partitioning of face space is a more beneficial way of using conventional ME for view-independent face recognition.