EBGM with fuzzy fusion on face recognition

Authors:
Jialiang Liu;Zhi-Qiang Liu
Affiliations:
The University of Melbourne, Australia;The University of Melbourne, Australia
Venue:
AI'05 Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence
Year:
2005

Citing 5
Cited 0

Computation of component image velocity from local phase information

International Journal of Computer Vision
Evolutionary Pursuit and Its Application to Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition: Features Versus Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Face recognition with radial basis function (RBF) neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Elastic Bunch Graph Matching (EBGM) is regarded as a successful method to perform recognition on 2D face images. It employs an indiscriminate, part-separated aggregation method to conclude the overall recognition from local recognition results on face parts. Supported by the experimental evidence from cognitive research, we consider the human face recognition is an aggregation process that combines the local recognitions together in a inter-dependent and collective manner rather than a indiscriminate and part-separated process. This paper presents a improved EBGM face recognition system with the use of fuzzy fusion techniques (fuzzy measure and fuzzy integral) as the collective aggregation method. Experimental result shows the EBGM with fuzzy fusion produces better recognition performance over the original EBGM.