Comparing Robustness of Pairwise and Multiclass Neural-Network Systems for Face Recognition. (30th December 2007)

• Record Type: Journal Article
• Authors: Uglov Uglov, J. J.; Jakaite Jakaite, L. L.; Schetinin Schetinin, V. V.; Maple Maple, C. C.
• Other Names: Plataniotis Plataniotis Konstantinos N. Konstantinos N. Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2008(2008)
• Publication Date: 2007-12-30
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2008/468693
• Languages: English
• ISSNs: 1687-6172

Abstract

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.