Conrad Sanderson - Publications

Refereed Publications

Tags

recent publications
natural language processing
automatic target recognition
face processing
speech processing
kernels
surveillance
information fusion
bioinformatics
misc

Some of the files below are copyrighted. While they are provided for the timely dissemination of scholarly and technical work on a non-commercial basis, you may download them only if you are entitled to do so by your arrangements with the various publishers.

recent publications

International Conference on Computer Analysis of Images and Patterns (CAIP), Germany, 2009.
Abstract | SpringerLink | PDF

We propose a low-complexity face synthesis technique which transforms a 2D frontal view image into views at specific poses, without recourse to computationally expensive 3D analysis or iterative fitting techniques that may fail to converge. The method first divides a given image into multiple overlapping blocks, followed by synthesising a non-frontal representation through applying a multivariate linear regression model on a low-dimensional representation of each block. To demonstrate one application of the proposed technique, we augment a frontal face verification system by incorporating multi-view reference (gallery) images synthesised from the frontal view. Experiments on the pose subset of the FERET database show considerable reductions in error rates, especially for large deviations from the frontal view.

.
A. Asthana, C. Sanderson, T. Gedeon, R. Goecke.
British Machine Vision Conference (BMVC), London, 2009.
PDF

International Conference on Biometrics, ICB 2009, LNCS 5558, pp. 199-208, 2009.
Abstract | SpringerLink | PDF

We propose a scalable face matching algorithm capable of dealing with faces subject to several concurrent and uncontrolled factors, such as variations in pose, expression, illumination, resolution, as well as scale and misalignment problems. Each face is described in terms of multi-region probabilistic histograms of visual words, followed by a normalised distance calculation between the histograms of two faces. We also propose a fast histogram approximation method which dramatically reduces the computational burden with minimal impact on discrimination performance. Experiments on the "Labeled Faces in the Wild" dataset (unconstrained environments) as well as FERET (controlled variations) show that the proposed algorithm obtains performance on par with a more complex method and displays a clear advantage over predecessor systems. Furthermore, the use of multiple regions (as opposed to a single overall region) improves accuracy in most cases, especially when dealing with illumination changes and very low resolution images. The experiments also show that normalised distances can noticeably improve robustness by partially counteracting the effects of image variations.

Cited by:

Andre Stoermer and Gerhard Rigoll.
Learning Weighted Similarity Measurements for Unconstrained Face Recognition.
IEEE International Conference on Image Processing, 2009.

.
C. Sanderson
VDM-Verlag, 2008.
ISBN 978-3-639-02769-3.
Abstract | Extract | Amazon

Over the last decade, interest in biometric based identification and verification systems has increased considerably. One application is the use of speech signals, face images or fingerprints in order to supplement security systems based on passwords. Biometric recognition can also be applied to other areas, such as passport control (immigration checkpoints), forensic work (to determine whether a biometric sample belongs to a suspect) and law enforcement applications (e.g. surveillance). While biometric systems based on face images and/or speech signals can be effective, their performance can degrade in the presence of challenging conditions. In face based systems this can be in the form of a change in the illumination direction and/or face pose variations. Multi-modal systems use more than one biometric at the same time. This is done for two main reasons -- to achieve better robustness and to increase discrimination power. This book can serve as a useful primer for face and speech processing, as well as information fusion. It reviews relevant backgrounds and reports research aimed at increasing the robustness of single- and multi-modal biometric identity verification systems.

natural language processing

Short Text Authorship Attribution via Sequence Kernels, Markov Chains and Author Unmasking: An Investigation.
C. Sanderson, S. Guenter.
International Conference on Empirical Methods in Natural Language Processing (EMNLP), Sydney, 2006.
Abstract | ACL Anthology | PDF
(this is an extended and revised version of the ICPR paper below)

We present an investigation of recently proposed character and word sequence kernels for the task of authorship attribution based on relatively short texts. Performance is compared with two corresponding probabilistic approaches based on Markov chains. Several configurations of the sequence kernels are studied on a relatively large dataset (50 authors), where each author covered several topics. Utilising Moffat smoothing, the two probabilistic approaches obtain similar performance, which in turn is comparable to that of character sequence kernels and is better than that of word sequence kernels. The results further suggest that when using a realistic setup that takes into account the case of texts which are not written by any hypothesised authors, the amount of training material has more influence on discrimination performance than the amount of test material. Moreover, we show that the recently proposed author unmasking approach is less useful when dealing with short texts.

On Authorship Attribution via Markov Chains and Sequence Kernels.
C. Sanderson, S. Guenter.
International Conference on Pattern Recognition (ICPR), Hong Kong, 2006.
Abstract | IEEE Xplore | PDF

We investigate the use of recently proposed character and word sequence kernels for the task of authorship attribution and compare their performance with two probabilistic approaches based on Markov chains of characters and words. Several configurations of the sequence kernels are studied using a relatively large dataset, where each author covered several topics. Utilising Moffat smoothing, the two probabilistic approaches obtain similar performance, which in turn is comparable to that of character sequence kernels and is better than that of word sequence kernels. The results further suggest that when using a realistic setup that takes into account the case of texts which are not written by any hypothesised authors, about 5000 reference words are required to obtain good discrimination performance.

An Efficient Alternative to SVM Based Recursive Feature Elimination with Applications in Natural Language Processing and Bioinformatics.
J. Bedo, C. Sanderson, A. Kowalczyk.
AI 2006: Advances in Artificial Intelligence,
Lecture Notes in Computer Science, Volume 4304/2006, Springer Berlin / Heidelberg.
Abstract | SpringerLink | PASCAL EPrint | PDF

The SVM based Recursive Feature Elimination (RFE-SVM) algorithm is a popular technique for feature selection, used in natural language processing and bioinformatics. Recently it was demonstrated that a small regularisation constant C can considerably improve the performance of RFE-SVM on microarray datasets. In this paper we show that further improvements are possible if the explicitly computable limit C -> 0 is used. We prove that in this limit most forms of SVM and ridge regression classifiers scaled by the factor 1/C converge to a centroid classifier. As this classifier can be used directly for feature ranking, in the limit we can avoid the computationally demanding recursion and convex optimisation in RFE-SVM. Comparisons on two text based author verification tasks and on three genomic microarray classification tasks indicate that this straightforward method can surprisingly obtain comparable (at times superior) performance and is about an order of magnitude faster.

Cited by:

L. Song et al.,
Gene selection via the BAHSIC family of algorithms.
Bioinformatics 23, July 2007, i490-i498.

automatic target recognition

On Statistical Approaches to Target Silhouette Classification in Difficult Conditions.
C. Sanderson, D. Gibbins, S. Searle.
Digital Signal Processing 18 (3) 2008, pp. 375-390.
ScienceDirect | PDF
(this is an extended and revised version of the ISSNIP paper below)

On Classifying Silhouettes in Adverse Conditions.
C. Sanderson, D. Gibbins.
International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), Melbourne, 2004.
IEEE Xplore | PDF

On Local Feature Approaches to Classifying Silhouettes in IR Images.
C. Sanderson, D. Gibbins.
CSSIP Commercial Report 34-05, Adelaide, Australia, 2005.

Silhouette Classification in Adverse Conditions.
C. Sanderson, D. Gibbins.
CSSIP Commercial Report 11-04, Adelaide, Australia, 2004.

face processing

Analysis and Modeling of Faces and Gestures (AMFG),
LNCS, Vol. 4778, 2007, pp. 276-289.
(held in conjunction with the International Conference on Computer Vision (ICCV), Rio de Janeiro, 2007)
Abstract | SpringerLink | PDF

A key problem for "face in the crowd" recognition from existing surveillance cameras in public spaces (such as mass transit centres) is the issue of pose mismatches between probe and gallery faces. In addition to accuracy, scalability is also important, necessarily limiting the complexity of face classification algorithms. In this paper we evaluate recent approaches to the recognition of faces at relatively large pose angles from a gallery of frontal images and propose novel adaptations as well as modifications. Specifically, we compare and contrast the accuracy, robustness and speed of an Active Appearance Model (AAM) based method (where realistic frontal faces are synthesized from non-frontal probe faces) against bag-of-features methods (which are local feature approaches based on block Discrete Cosine Transforms and Gaussian Mixture Models). We show a novel approach where the AAM based technique is sped up by directly obtaining pose-robust features, allowing the omission of the computationally expensive and artefact producing image synthesis step. Additionally, we adapt a histogram-based bag-of-features technique to face classification and contrast its properties to a previously proposed direct bag-of-features method. We also show that the two bag-of-features approaches can be considerably sped up, without a loss in classification accuracy, via an approximation of the exponential function. Experiments on the FERET and PIE databases suggest that the bag-of-features techniques generally attain better performance, with significantly lower computational loads. The histogram-based bag-of-features technique is capable of achieving an average recognition accuracy of 89% for pose angles of around 25 degrees.

On Transforming Statistical Models for Non-Frontal Face Verification.
C. Sanderson, S. Bengio, Y. Gao.
Pattern Recognition 39 (2) 2006.
Abstract | ScienceDirect | PDF
(this is an extended and revised version of the ICIP paper below)

We address the pose mismatch problem which can occur in face verification systems that have only a single (frontal) face image available for training. In the framework of a Bayesian classifier based on mixtures of gaussians, the problem is tackled through extending each frontal face model with artificially synthesized models for non-frontal views. The synthesis methods are based on several implementations of Maximum Likelihood Linear Regression (MLLR), as well as standard multi-variate linear regression (LinReg). All synthesis techniques rely on prior information and learn how face models for the frontal view are related to face models for non-frontal views. The synthesis and extension approach is evaluated by applying it to two face verification systems: a holistic system (based on PCA-derived features) and a local feature system (based on DCT-derived features). Experiments on the FERET database suggest that for the holistic system, the LinReg based technique is more suited than the MLLR based techniques; for the local feature system, the results show that synthesis via a new MLLR implementation obtains better performance than synthesis based on traditional MLLR. The results further suggest that extending frontal models considerably reduces errors. It is also shown that the local feature system is less affected by view changes than the holistic system; this can be attributed to the parts based representation of the face, and, due to the classifier based on mixtures of gaussians, the lack of constraints on spatial relations between the face parts, allowing for deformations and movements of face areas.

Cited by:

S. Lucey, T. Chen.
A viewpoint invariant, sparsely registered, patch based, face verifier.
International Journal of Computer Vision 80 (1), 2008, 58-71.
S.J.D. Prince, J.H. Elder, J. Warrell, F.M. Felisberti.
Tied factor analysis for face recognition across large pose differences.
IEEE Transactions on Pattern Analysis and Machine Intelligence 30 (6) 2008, 970-984.
N.A. Fox, R. Gross, J.F. Cohn. R.B. Reilly.
Robust Biometric Person Identification Using Automatic Classifier Fusion of Speech, Mouth, and Face Experts.
IEEE Transactions on Multimedia 9 (4) 2007, 701-714.
P.S. Aleksic, A.K. Katsaggelos.
Audio-Visual Biometrics.
Proceedings of the IEEE 94 (11) 2006, 2025-2044.
A.K. Sao, B. Yegnanaarayana.
Template Matching Approach for Pose Problem in Face Verification.
Multimedia Content Representation, Classification and Security. Lecture Notes in Computer Science 4105/2006, pp. 191-198, Springer Berlin / Heidelberg, 2006.
M. Shi, A. Bermak.
An Efficient Digital VLSI Implementation of Gaussian Mixture Models-Based Classifiers.
IEEE Transactions on Very Large Scale Integration (VLSI) Systems 15 (9) 2006, 962-974.

Statistical Transformations of Frontal Models for Non-Frontal Face Verification.
C. Sanderson, S. Bengio.
IEEE International Conference on Image Processing (ICIP), Singapore, 2004.
IEEE Xplore | PDF

User Authentication via Adapted Statistical Models of Face Images.
F. Cardinaux, C. Sanderson, S. Bengio.
IEEE Transactions on Signal Processing 54 (1) 2006.
Abstract | IEEE Xplore | PDF
(this is an extended and revised version of the AFGR paper below)

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.

Cited by:

P.S. Aleksic, A.K. Katsaggelos.
Audio-Visual Biometrics.
Proceedings of the IEEE 94 (11) 2006, 2025-2044.
Y. Rodriguez, F. Cardinaux, S. Bengio, J. Mariethoz.
Measuring the performance of face localization systems. Image and Vision Computing 24 (8) 2006, 882-893.
M. Shi, A. Bermak.
An Efficient Digital VLSI Implementation of Gaussian Mixture Models-Based Classifiers.
IEEE Transactions on Very Large Scale Integration (VLSI) Systems 15 (9) 2006, 962-974.

Face Verification Using Adapted Generative Models.
F. Cardinaux, C. Sanderson, S. Bengio.
IEEE International Conference on Face and Gesture Recognition (AFGR), Seoul, 2004.
IEEE Xplore | PDF

On Local Features for GMM Based Face Verification.
C. Sanderson, M. Saban, Y. Gao.
International Conference on Information Technology and Applic., Sydney, 2005.
Abstract | IEEE Xplore | PDF

It has been recently shown that local feature approaches to face verification are considerably more robust than holistic approaches, in terms of translations (caused by automatic face localization) and pose variations. In this paper, we first investigate whether features based on local principal component analysis (LPCA) are more discriminative than features based on the 2D discrete cosine transform (2D DCT). We also investigate several methods for modifying the two feature extraction techniques in order to counteract the effects of linear and non-linear illumination changes, without losing discriminative information. Results on the XM2VTS database show that when using a Bayesian classifier based on Gaussian mixture models (GMMs), the performances of 2D DCT and LPCA techniques are quite similar, suggesting that the 2D DCT technique is preferable due to its lower computational complexity. When using 8x8 blocks, modifying the 2D DCT and LPCA techniques by removing the first coefficient, which is the most affected by illumination changes, enhances robustness with little change in discrimination ability; removing further coefficients causes a noticeable reduction in performance on clean images and provides little gain in robustness. When using the 2D DCT with 16x16 blocks, the first three coefficients need to be removed in order to achieve good robustness. It is further shown that contrary to previously published results, the use of deltas of low-order coefficients (to alleviate performance losses caused by removing coefficients) can adversely affect robustness.

Augmenting Frontal Face Models for Non-Frontal Verification.
C. Sanderson, S. Bengio.
Workshop on Multi-Modal User Authentication (MMUA), Santa Barbara, 2003.

Robust Features for Frontal Face Authentication in Difficult Image Conditions.
C. Sanderson, S. Bengio.
Audio- and Video-Based Biometric Person Authentication (AVBPA),
Lecture Notes in Computer Science, Vol. 2688/2003, Springer Berlin / Heidelberg.
Abstract | SpringerLink | PDF

In this paper we extend the recently proposed DCT-mod2 feature extraction technique (which utilizes polynomial coefficients derived from 2D DCT coefficients obtained from horizontally & vertically neighbouring blocks) via the use of various windows and diagonally neighbouring blocks. We also propose enhanced PCA, where traditional PCA feature extraction is combined with DCT-mod2. Results using test images corrupted by a linear and a non-linear illumination change, white Gaussian noise and compression artefacts, show that use of diagonally neighbouring blocks and windowing is detrimental to robustness against illumination changes while being useful for increasing robustness against white noise and compression artefacts. We also show that the enhanced PCA technique retains all the positive aspects of traditional PCA (that is, robustness against white noise and compression artefacts) while also being robust to illumination changes; moreover, enhanced PCA outperforms PCA with histogram equalisation pre-processing.

Comparison of MLP and GMM Classifiers for Face Verification on XM2VTS (AVBPA).
F. Cardinaux, C. Sanderson, S. Marcel.
International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA), Guildford, 2003.
SpringerLink | PDF

Fast Features for Face Authentication Under Illumination Direction Changes.
C. Sanderson, K. K. Paliwal.
Pattern Recognition Letters 24 (14) 2003.
(this is an extended and revised version of the ICIP paper below)

Polynomial Features for Robust Face Authentication.
C. Sanderson, K. K. Paliwal.
IEEE International Conference on Image Processing (ICIP), Rochester, 2002.

speech processing

Spectral Subband Centroids as Complementary Features for Speaker Authentication.
N. Poh,C. Sanderson, S. Bengio.
International Conference on Biometric Authentication (ICBA), Hong Kong, 2004.
Abstract | SpringerLink | PDF

Most conventional features used in speaker authentication are based on estimation of spectral envelopes in one way or another, e.g., Mel-scale Filterbank Cepstrum Coefficients (MFCCs), Linear-scale Filterbank Cepstrum Coefficients (LFCCs) and Relative Spectral Perceptual Linear Prediction (RASTA-PLP). In this study, Spectral Subband Centroids (SSCs) are examined. These features are the centroid frequency in each subband. They have properties similar to formant frequencies but are limited to a given subband. Empirical experiments carried out on the NIST2001 database using SSCs, MFCCs, LFCCs and their combinations by concatenation suggest that SSCs are somewhat more robust compared to conventional MFCC and LFCC features as well as being partially complementary.

Speech & Face Based Biometric Authentication at IDIAP.
C. Sanderson, S. Bengio, H. Bourlard, J. Mariethoz, R. Collobert, M. F. BenZeghiba, F. Cardinaux, S. Marcel.
IEEE International Conference on Multimedia & Expo (ICME), Baltimore, 2003.
IEEE Xplore | PDF

Japanese Phoneme Recognition Experiments on ATR's Travel Task (SDB) using HTK v2.02.
C. Sanderson, H. Singer.
Technical Report TR-IT-0223, ATR Interpreting Telecommunications Research Laboratories, Kyoto, Japan, 1997.

kernels

surveillance

IEEE Workshop on Signal Processing Applications for Public Security and Forensics, Washington D.C., pp. 12-15, 2007.
Abstract | IEEE Xplore

Intelligent Surveillance Systems are attracting unprecedented attention from research and industry. In this paper, we describe a real-life trial system where various video analytic systems are used to detect events and objects of interests in a mass transport environment. The system configuration and architecture of this system is presented. In addition to implementation and scalability challenges, we discuss issues related to on-going trials in public spaces incorporating existing surveillance hardware.

IEEE Conference on Advanced Video and Signal based Surveillance, London, 2007.

Proceedings of IEEE Conference on Advanced Video and Signal based Surveillance, London, 2007.

Electronic Letters on Computer Vision and Image Analysis (ELCVIA), Vol. 6, No. 3, 2007, pp. 30-41.

S. Lucey, T. Chen.
A viewpoint invariant, sparsely registered, patch based, face verifier.
International Journal of Computer Vision 80 (1), 2008, 58-71.
S.J.D. Prince, J.H. Elder, J. Warrell, F.M. Felisberti.
Tied factor analysis for face recognition across large pose differences.
IEEE Transactions on Pattern Analysis and Machine Intelligence 30 (6) 2008, 970-984.
N.A. Fox, R. Gross, J.F. Cohn. R.B. Reilly.
Robust Biometric Person Identification Using Automatic Classifier Fusion of Speech, Mouth, and Face Experts.
IEEE Transactions on Multimedia 9 (4) 2007, 701-714.
P.S. Aleksic, A.K. Katsaggelos.
Audio-Visual Biometrics.
Proceedings of the IEEE 94 (11) 2006, 2025-2044.
A.K. Sao, B. Yegnanaarayana.
Template Matching Approach for Pose Problem in Face Verification.
Multimedia Content Representation, Classification and Security. Lecture Notes in Computer Science 4105/2006, pp. 191-198, Springer Berlin / Heidelberg, 2006.
M. Shi, A. Bermak.
An Efficient Digital VLSI Implementation of Gaussian Mixture Models-Based Classifiers.
IEEE Transactions on Very Large Scale Integration (VLSI) Systems 15 (9) 2006, 962-974.

information fusion

<tr> <td class="myrow" valign="top"> <a class="hidden" href="pdfs/icassp01_conrad.pdf">Noise Compensation in a Multi-Modal Verification System</a>. C. Sanderson, K. K. Paliwal. Proc. ICASSP 2001. <a href="pdfs/icassp01_conrad.pdf">PDF</a> </td> </tr>

.
C. Sanderson
VDM-Verlag, 2008.
ISBN 978-3-639-02769-3.
Abstract | Chapter 1 | Amazon

Over the last decade, interest in biometric based identification and verification systems has increased considerably. One application is the use of speech signals, face images or fingerprints in order to supplement security systems based on passwords. Biometric recognition can also be applied to other areas, such as passport control (immigration checkpoints), forensic work (to determine whether a biometric sample belongs to a suspect) and law enforcement applications (e.g. surveillance). While biometric systems based on face images and/or speech signals can be effective, their performance can degrade in the presence of challenging conditions. In face based systems this can be in the form of a change in the illumination direction and/or face pose variations. Multi-modal systems use more than one biometric at the same time. This is done for two main reasons -- to achieve better robustness and to increase discrimination power. This book can serve as a useful primer for face and speech processing, as well as information fusion. It reviews relevant backgrounds and reports research aimed at increasing the robustness of single- and multi-modal biometric identity verification systems.

Digital Signal Processing 14 (5) 2004, 449-480.
Abstract | PDF
(this article recevied the Most Cited Paper Award)

This article first provides an overview of important concepts in the field of information fusion, followed by a review of milestones in audio-visual person identification and verification. Several recent adaptive and non-adaptive techniques for reaching the verification decision (i.e., to accept or reject the claimant), based on speech and face information, are then evaluated in clean and noisy audio conditions on a common database; it is shown that in clean conditions most of the non-adaptive approaches provide similar performance and in noisy conditions most exhibit a severe deterioration in performance; it is also shown that current adaptive approaches are either inadequate or utilize restrictive assumptions. A new category of classifiers is then introduced, where the decision boundary is fixed but constructed to take into account how the distributions of opinions are likely to change due to noisy conditions; compared to a previously proposed adaptive approach, the proposed classifiers do not make a direct assumption about the type of noise that causes the mismatch between training and testing conditions.

Cited by (subset):

N.A. Fox, R. Gross, J.F. Cohn. R.B. Reilly.
Robust Biometric Person Identification Using Automatic Classifier Fusion of Speech, Mouth, and Face Experts.
IEEE Transactions on Multimedia 9 (4) 2007, 701-714.
P.S. Aleksic, A.K. Katsaggelos.
Audio-Visual Biometrics.
Proceedings of the IEEE 94 (11) 2006, 2025-2044.

Structurally Noise Resistant Classifier for Multi-Modal Person Verification.
C. Sanderson, K. K. Paliwal.
Pattern Recognition Letters 24 (16) 2003.

Noise Resistant Audio-Visual Verification via Structural Constraints.
C. Sanderson,K. K. Paliwal.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hong Kong, 2003.

bioinformatics

L. Song et al.,
Gene selection via the BAHSIC family of algorithms.
Bioinformatics 23, July 2007, i490-i498.

.
J. Bedo, T. Caetano, B. Parker, C. Sanderson, P. Sunehag, A. Kowalczyk.
Poster, presented at the 14th Annual Conference on Intelligent Systems for Molecular Biology (ISMB), Fortaleza, Brazil, 2006.
abstract

misc

Face Authentication Competition on the BANCA Database.
K. Messer, J. Kittler, M. Sadeghi, M. Hamouz, A. Kostyn, S. Marcel, S. Bengio, F. Cardinaux, C. Sanderson, N. Poh, Y. Rodriguez, K. Kryszczuk, J. Czyz, L. Vandendorpe, J. Ng, H. Cheung, B. Tang.
International Conference on Biometric Authentication (ICBA), Hong Kong, 2004.
SpringerLink | PDF

Face Verification Competition on the XM2VTS Database.
K. Messer, J. Kittler, M. Sadeghi, S. Marcel, C. Marcel, S. Bengio, F. Cardinaux, C. Sanderson, J. Czyz, L. Vandendorpe, S. Srisuk, M. Petrou, W. Kurutach, A. Kadyrov, R. Paredes, B. Kepenekci, F. B. Tek, G. B. Akar, F. Deravi, N. Mavity.
International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA), Guildford, 2003.
SpringerLink | PDF

Automatic Person Verification Using Speech and Face Information.
C. Sanderson.
PhD Thesis, Griffith University, Queensland, Australia, 2003.
PDF | UQ eSpace