An efficient digital VLSI implementation of Gaussian mixture models-based classifier
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
On statistical approaches to target silhouette classification in difficult conditions
Digital Signal Processing
Labeled images verification using Gaussian mixture models
Proceedings of the 2009 ACM symposium on Applied Computing
Multi-Region Probabilistic Histograms for Robust and Scalable Identity Inference
ICB '09 Proceedings of the Third International Conference on Advances in Biometrics
Bayesian Networks to Combine Intensity and Color Information in Face Recognition
ICB '09 Proceedings of the Third International Conference on Advances in Biometrics
A novel statistical generative model dedicated to face recognition
Image and Vision Computing
Discrete sine transform and alternative local linear regression for face recognition
SPPRA '08 Proceedings of the Fifth IASTED International Conference on Signal Processing, Pattern Recognition and Applications
On combination of face authentication experts by a mixture of quality dependent fusion classifiers
MCS'07 Proceedings of the 7th international conference on Multiple classifier systems
Biometric person authentication is a multiple classifier problem
MCS'07 Proceedings of the 7th international conference on Multiple classifier systems
Towards pose-invariant 2D face classification for surveillance
AMFG'07 Proceedings of the 3rd international conference on Analysis and modeling of faces and gestures
Automatic face analysis system based on face recognition and facial physiognomy
ICHIT'06 Proceedings of the 1st international conference on Advances in hybrid information technology
Quality controlled multimodal fusion of biometric experts
CIARP'07 Proceedings of the Congress on pattern recognition 12th Iberoamerican conference on Progress in pattern recognition, image analysis and applications
An evaluation of video-to-video face verification
IEEE Transactions on Information Forensics and Security
ICB'06 Proceedings of the 2006 international conference on Advances in Biometrics
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Face authentication with salient local features and static Bayesian network
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Overlapping local phase feature (OLPF) for robust face recognition in surveillance
ACIVS'12 Proceedings of the 14th international conference on Advanced Concepts for Intelligent Vision Systems
Fusing matching and biometric similarity measures for face diarization in video
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
Hi-index | 35.68 |
It has been previously demonstrated that systems based on local features and relatively complex statistical models, namely, one-dimensional (1-D) hidden Markov models (HMMs) and pseudo-two-dimensional (2-D) HMMs, are suitable for face recognition. Recently, a simpler statistical model, namely, the Gaussian mixture model (GMM), was also shown to perform well. In much of the literature devoted to these models, the experiments were performed with controlled images (manual face localization, controlled lighting, background, pose, etc). However, a practical recognition system has to be robust to more challenging conditions. In this article we evaluate, on the relatively difficult BANCA database, the performance, robustness and complexity of GMM and HMM-based approaches, using both manual and automatic face localization. We extend the GMM approach through the use of local features with embedded positional information, increasing performance without sacrificing its low complexity. Furthermore, we show that the traditionally used maximum likelihood (ML) training approach has problems estimating robust model parameters when there is only a few training images available. Considerably more precise models can be obtained through the use of Maximum a posteriori probability (MAP) training. We also show that face recognition techniques which obtain good performance on manually located faces do not necessarily obtain good performance on automatically located faces, indicating that recognition techniques must be designed from the ground up to handle imperfect localization. Finally, we show that while the pseudo-2-D HMM approach has the best overall performance, authentication time on current hardware makes it impractical. The best tradeoff in terms of authentication time, robustness and discrimination performance is achieved by the extended GMM approach.