Face recognition using ensembles of networks
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 50-54 vol.4
- https://doi.org/10.1109/icpr.1996.547232
Abstract
We describe a novel approach for fully automated face recognition and show its feasibility on a large database of facial images (FERET). Our approach, based on a hybrid architecture consisting of an ensemble of radial basis function (RBF) neural networks and inductive decision trees, combines the merits of "abstractive" features with those of "holistic" template matching. The benefits of our architecture include: 1) robust detection of facial landmarks using decision trees, and 2) robust face recognition using consensus methods over ensembles of RBF networks. Experiments carried out using k-fold cross validation on a large database consisting of 748 images corresponding to 374 subjects, among them 11 duplicates, yield on the average 87% correct match, and 99% correct surveillance ("verification").Keywords
This publication has 5 references indexed in Scilit:
- Human and machine recognition of faces: a surveyProceedings of the IEEE, 1995
- Democracy in neural nets: Voting schemes for classificationNeural Networks, 1994
- The Meta-Pi network: building distributed knowledge representations for robust multisource pattern recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Automatic recognition and analysis of human faces and facial expressions: a surveyPattern Recognition, 1992
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991