Bayesian score level fusion for facial recognition

Partial occlusions, changing lighting conditions, or rapid motion of persons are some reasons why the recognition rate of a facial recognition (FR) system can be very low. One approach that has gained increased interest in the recent years for compensating the limitations of a single system is to fuse the detections of multiple FR systems. In this paper, a novel fusion algorithm operating on match score level is proposed that follows Bayesian inference and decision theory. It is designed for on-line recognition and facilitates the incorporation of temporal correlation between detections. The proposed approach is compared against the state-of-the-art by means of standard FR benchmarks and an extensive person detection experiment in an office environment.

[1]  Anil K. Jain,et al.  Biometric fusion: Does modeling correlation really matter? , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[2]  M. Huber.  On-Line Dispersion Source Estimation Using Adaptive Gaussian Mixture Filter , 2014 .

[3]  Carlo Sansone,et al.  Improving the Accuracy of a Score Fusion Approach Based on Likelihood Ratio in Multimodal Biometric Systems , 2009, ICIAP.

[4]  Nalini K. Ratha,et al.  QPLC: A novel multimodal biometric score fusion method , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[5]  Pingzhi Fan,et al.  Performance evaluation of score level fusion in multimodal biometric systems , 2010, Pattern Recognit..

[6]  Abdelhak M. Zoubir,et al.  Collaborative multi-camera face recognition and tracking , 2015, 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[7]  Arun Ross,et al.  On the Dynamic Selection of Biometric Fusion Algorithms , 2010, IEEE Transactions on Information Forensics and Security.

[8]  Horst Bunke,et al.  Combination of Classifiers on the Decision Level for Face Recognition , 1996 .

[9]  Anil K. Jain,et al.  Likelihood Ratio-Based Biometric Score Fusion , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[11]  Shin Ishii,et al.  On-line EM Algorithm for the Normalized Gaussian Network , 2000, Neural Computation.

[12]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[13]  Luiz Eduardo Soares de Oliveira,et al.  Combining different biometric traits with one-class classification , 2009, Signal Process..

[14]  Yasushi Makihara,et al.  Score-level fusion based on the direct estimation of the Bayes error gradient distribution , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[15]  Anil K. Jain,et al.  A Principled Approach to Score Level Fusion in Multimodal Biometric Systems , 2005, AVBPA.

[16]  Savvas Argyropoulos,et al.  Four Machine Learning Algorithms for Biometrics Fusion: A Comparative Study , 2012, Appl. Comput. Intell. Soft Comput..

[17]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[18]  Andrew R. Barron,et al.  Mixture Density Estimation , 1999, NIPS.

[19]  Roberto Brunelli,et al.  Person identification using multiple cues , 1995, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  L. Hong,et al.  Can multibiometrics improve performance , 1999 .

[21]  Tieniu Tan,et al.  Combining Face and Iris Biometrics for Identity Verification , 2003, AVBPA.

[22]  Pedro M. Domingos,et al.  On the Optimality of the Simple Bayesian Classifier under Zero-One Loss , 1997, Machine Learning.

[23]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[24]  Arun Ross,et al.  Fusion in Multibiometric Identification Systems: What about the Missing Data? , 2009, ICB.

[25]  Raymond N. J. Veldhuis,et al.  Robust Biometric Score Fusion by Naive Likelihood Ratio via Receiver Operating Characteristics , 2013, IEEE Transactions on Information Forensics and Security.