Name
Abstract | ||
|---|---|---|
We compare two classifier approaches, namely classifiers based on Multi Layer Perceptrons (MLPs) and Gaussian Mixture Models (GMMs), for use in a face verification system. The comparison is carried out in terms of performance, robustness and practicability. Apart from structural differences, the two approaches use different training criteria; the MLP approach uses a discriminative criterion, while the GMM approach uses a combination of Maximum Likelihood (ML) and Maximum a Posteriori (MAP) criteria. Experiments on the XM2VTS database show that for low resolution faces the MLP approach has slightly lower error rates than the GMM approach; however, the GMM approach easily outperforms the MLP approach for high resolution faces and is significantly more robust to imperfectly located faces. The experiments also show that the computational requirements of the GMM approach can be significantly smaller than the MLP approach at a cost of small loss of performance. |
Year | Venue | Keywords |
|---|---|---|
2003 | AVBPA | computational requirement,low resolution,xm2vts database show,maximum likelihood,gaussian mixture models,classifier approach,high resolution,gmm classifier,multi layer perceptrons,gmm approach,mlp approach,face verification,gaussian mixture model,multi layer perceptron,vision |
Field | DocType | Volume |
Pattern recognition,Computer science,Word error rate,Robustness (computer science),Artificial intelligence,Maximum a posteriori estimation,Classifier (linguistics),Artificial neural network,Perceptron,Discriminative model,Machine learning,Mixture model | Conference | 2688 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-40302-7 | 49 |
PageRank | References | Authors |
3.82 | 10 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fabien Cardinaux | 1 | 279 | 19.00 |
| Conrad Sanderson | 2 | 1546 | 83.46 |
| Sébastien Marcel | 3 | 1984 | 123.84 |