Improving Classification with Class-Independent Quality Measures: Q-stack in Face Verification

Existing approaches to classification with signal quality measures make a clear distinction between the single- and multiple classifier scenarios. This paper presents an uniform approach to dichotomization based on the concept of stacking, Q-stack, which makes use of classindependent signal quality measures and baseline classifier scores in order to improve classification in uni- and multimodal systems alike. In this paper we demonstrate the application of Q-stack on the task of biometric identity verification using face images and associated quality measures. We show that the use of the proposed technique allows for reducing the error rates below those of baseline classifiers in single- and multiclassifier scenarios. We discuss how Q-stack can serve as a generalized framework in any single, multiple, and multimodal classifier ensemble.

[1]  Krzysztof Kryszczuk,et al.  Gradient-based image segmentation for face recognition robust to directional illumination , 2005, Visual Communications and Image Processing.

[2]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[3]  Wei-Yun Yau,et al.  Fusion of Auxiliary Information for Multi-modal Biometrics Authentication , 2004, ICBA.

[4]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[5]  Samy Bengio,et al.  Confidence measures for multimodal identity verification , 2002, Inf. Fusion.

[6]  Alfred C. Weaver,et al.  Biometric authentication , 2006, Computer.

[7]  Elham Tabassi,et al.  Performance of Biometric Quality Measures , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Krzysztof Kryszczuk,et al.  On combining evidence for reliability estimation in face verification , 2006, 2006 14th European Signal Processing Conference.

[9]  Anil K. Jain,et al.  Quality-based Score Level Fusion in Multibiometric Systems , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[10]  Julian Fierrez.  Adapted fusion schemes for multimodal biometric authentication (Esquemas adaptados de fusión para autenticación biométrica multimodal) , 2006 .

[11]  Thierry Pun,et al.  Error exponent analysis of person identification based on fusion of dependent/independent modalities: multiple hypothesis testing case , 2008, Electronic Imaging.

[12]  Lawrence M Wein,et al.  Using fingerprint image quality to improve the identification performance of the U.S. Visitor and Immigrant Status Indicator Technology Program. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Conrad Sanderson,et al.  Automatic Person Verification Using Speech and Face Information , 2003 .

[14]  Ralph Gross,et al.  An Image Preprocessing Algorithm for Illumination Invariant Face Recognition , 2003, AVBPA.

[15]  Thierry Pun,et al.  Error exponent analysis of person identification based on fusion of dependent/independent modalities , 2007, Electronic Imaging.

[16]  Julian Fiérrez,et al.  Biosec baseline corpus: A multimodal biometric database , 2007, Pattern Recognit..

[17]  Josef Kittler,et al.  On Combination of Face Authentication Experts by a Mixture of Quality Dependent Fusion Classifiers , 2007, MCS.

[18]  Mark J. F. Gales,et al.  Robust continuous speech recognition using parallel model combination , 1996, IEEE Trans. Speech Audio Process..

[19]  Krzysztof Kryszczuk,et al.  Q-stack: Uni- and Multimodal Classifier Stacking with Quality Measures , 2007, MCS.