Article

Q-stack: uni- and multimodal classifier stacking with quality measures

Authors:

Krzysztof Kryszczuk,

Andrzej DrygajloAuthors Info & Claims

MCS'07: Proceedings of the 7th international conference on Multiple classifier systems

Pages 367 - 376

Published: 23 May 2007 Publication History

Abstract

The use of quality measures in pattern classification has recently received a lot of attention in the areas where the deterioration of signal quality is one of the primary causes of classification errors. An example of such domain is biometric authentication. In this paper we provide a novel theoretical paradigm of using quality measures to improve both uni- and multimodal classification. We introduce Q - stack, a classifier stacking method in which feature similarity scores obtained from the first classification step are used in ensemble with the quality measures as features for the second classifier. Using two-class, synthetically generated data, we demonstrate how Q - stack helps significantly improve both uni- and multimodal classification in the presence of signal quality degradation.

References

[1]

Duda, R., Hart, P., Stork, D.: Pattern Classification. 2nd edn. Wiley Interscience, New York (2001).

Digital Library

[2]

Ross, A., Jain, A.: Multimodal biometrics: An overview. In: Proc. of 12th European Signal Processing Conference (EUSIPCO), Vienna, Austria (2004) 1221-1224.

[3]

Kryszczuk, K., Drygajlo, A.: Gradient-based image segmentation for face recognition robust to directional illumination. In: Visual communications and image processing 2005 : 12-15 July 2005, Beijing, China. (2005).

[4]

Poh, N.: Multi-system Biometric Authentication: Optimal Fusion and User-Specific Information. PhD thesis, Swiss Federal Institute of Technology Lausanne EPFL (2006).

[5]

Fierrez-Aguilar, J.: Adapted Fusion Schemes for Multimodal Biometric Authentication. PhD thesis, Universidad Politecnica de Madrid (2006).

[6]

Polikar, R.: Ensemble based systems in decision making. IEEE Circuits and Systems Magazine 6 (2006) 21-45.

[7]

Jain, A.K., Ross, A.: Multibiometric systems. Commun. ACM 47 (2004) 34-40.

Digital Library

[8]

Alkoot, F.M., Kittler, J.: Experimental evaluation of expert fusion strategies. Pattern Recogn. Lett. 20 (1999) 1361-1369.

Digital Library

[9]

Bengio, S., Marcel, C., Marcel, S., Mariethoz, J.: Confidence measures for multimodal identity verification. Information Fusion 3 (2002) 267-276.

[10]

Richiardi, J., Prodanov, P., Drygajlo, A.: Speaker verification with confidence and reliability measures. In: 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. Volume 1. (2006) 641-644.

[11]

Poh, N., Bengio, S.: Improving fusion with margin-derived confidence in biometric authentication tasks. In: Proceedings of the AVBPA, Rye Brook NY, USA (2005).

Digital Library

[12]

Kryszczuk, K., Richiardi, J., Prodanov, P., Drygajlo, A.: Error handling in multimodal biometric systems using reliability measures. In: 13th European Signal Processing Conference (EUSIPCO 2005), Antalya, Turkey (2005).

[13]

Toh, K.A., Yau,W.Y., Lim, E., Chen, L., Ng, C.H.: Fusion of auxiliary information for multi-modal biometrics authentication. In: Proceedings of International Conference on Biometrics. Lecture Notes in Computer Science, Hong Kong, Springer (2004) 678-685.

[14]

Kryszczuk, K., Drygajlo, A.: Reliability measures and error prediction in biometric identity verification. submitted to: Journal of Signal Processing (2006).

[15]

Tax, D., Duin, R.: Using two-class classifiers for multiclass classification. In: Proceedings, 16th International Conference on Pattern Recognition. (2002).

[16]

Kryszczuk, K., Drygajlo, A.: On combining evidence for reliability estimation in face verification. In: Proc. of the EUSIPCO 2006, Florence (2006).

[17]

Koval, O., Voloshynovskiy, S., Pun, T.: Error exponent analysis of person identification based on fusion of dependent/independent modalities. In: In Proceedings of SPIE Photonics West, Electronic Imaging 2006, Multimedia Content Analysis, Management, and Retrieval 2006 (EI122). (2006).

Cited By

Shu XXie GLi ZTang J(2016)Age progressionNeurocomputing10.1016/j.neucom.2016.01.101208:C(249-261)Online publication date: 5-Oct-2016
https://dl.acm.org/doi/10.1016/j.neucom.2016.01.101
Drygajlo ALi WZhu K(2009)Verification of aging faces using local ternary patterns and Q-stack classifierProceedings of the 2009 joint COST 2101 and 2102 international conference on Biometric ID management and multimodal communication10.5555/1812740.1812745(25-32)Online publication date: 16-Sep-2009
https://dl.acm.org/doi/10.5555/1812740.1812745
Kryszczuk KDrygajlo A(2007)Improving classification with class-independent quality measuresProceedings of the 2007 international conference on Advances in Biometrics10.5555/2391659.2391785(1124-1133)Online publication date: 27-Aug-2007
https://dl.acm.org/doi/10.5555/2391659.2391785

Q-stack: uni- and multimodal classifier stacking with quality measures
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches

Recommendations

Improving classification with class-independent quality measures: Q-stack in face verification
ICB'07: Proceedings of the 2007 international conference on Advances in Biometrics

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, ...
Incremental construction of classifier and discriminant ensembles

We discuss approaches to incrementally construct an ensemble. The first constructs an ensemble of classifiers choosing a subset from a larger set, and the second constructs an ensemble of discriminants, where a classifier is used for some classes only. ...
Forests of nested dichotomies

Ensemble methods are often able to generate more accurate classifiers than the individual classifiers. In multiclass problems, it is possible to obtain an ensemble combining binary classifiers. It is sensible to use a multiclass method for constructing ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

MCS'07: Proceedings of the 7th international conference on Multiple classifier systems

May 2007

524 pages

ISBN:9783540724810

Editors:
Michal Haindl
Academy of Sciences CR, Institute of Information Theory and Automation, Prague, Czech Republic
,
Josef Kittler
University of Surrey, Centre for Vision, Speech and Signal Processing, Guildford, Surrey, UK
,
Fabio Roli
University of Cagliari, Department of Electrical and Electronic Engineering, Cagliari, Italy

Sponsors

EU IST FP6 BioSecure Network of Excellence
EU IST FP6 MUSCLE Network of Excellence
IAPR: International Association for Pattern Recognition
University of Surrey
University of Cagliari: University of Cagliari

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 23 May 2007

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 18 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Shu XXie GLi ZTang J(2016)Age progressionNeurocomputing10.1016/j.neucom.2016.01.101208:C(249-261)Online publication date: 5-Oct-2016
https://dl.acm.org/doi/10.1016/j.neucom.2016.01.101
Drygajlo ALi WZhu K(2009)Verification of aging faces using local ternary patterns and Q-stack classifierProceedings of the 2009 joint COST 2101 and 2102 international conference on Biometric ID management and multimodal communication10.5555/1812740.1812745(25-32)Online publication date: 16-Sep-2009
https://dl.acm.org/doi/10.5555/1812740.1812745
Kryszczuk KDrygajlo A(2007)Improving classification with class-independent quality measuresProceedings of the 2007 international conference on Advances in Biometrics10.5555/2391659.2391785(1124-1133)Online publication date: 27-Aug-2007
https://dl.acm.org/doi/10.5555/2391659.2391785

View Options

View options

Media

Figures

Other

Tables

View Table of Contents