Comparing robustness of pairwise and multiclass neural-network systems for face recognition

Authors:
J. Uglov;L. Jakaite;V. Schetinin;C. Maple
Affiliations:
Computing and Information System Department, University of Bedfordshire, Luton, UK;Computing and Information System Department, University of Bedfordshire, Luton, UK;Computing and Information System Department, University of Bedfordshire, Luton, UK;Computing and Information System Department, University of Bedfordshire, Luton, UK
Venue:
EURASIP Journal on Advances in Signal Processing
Year:
2008

Citing 4
Cited 0

Classification by pairwise coupling

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

IEEE Transactions on Pattern Analysis and Machine Intelligence
Biometric authentication: a machine learning approach

Biometric authentication: a machine learning approach
Robust coding schemes for indexing and retrieval from large face databases

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Noise, corruptions, and variations in face images can seriously hurt the performance of face-recognition systems. To make these systems robust to noise and corruptions in image data, multiclass neural networks capable of learning from noisy data have been suggested. However on large face datasets such systems cannot provide the robustness at a high level. In this paper, we explore a pairwise neural-network system as an alternative approach to improve the robustness of face recognition. In our experiments, the pairwise recognition system is shown to outperform the multiclass-recognition system in terms of the predictive accuracy on the test face images.