About AMP Lab        Projects        Downloads        Publications        People        Links

Group Member

Dr. Simon Lucey
 Research Scientist (Ph.D.)

Personal Homepage: http://www.andrew.cmu.edu/user/slucey
Email: slucey AT ieee.org
Office: Hamburg Hall AA216
Lab: Porter Hall B6
Phone: 412-268-2889
Fax: 412-268-3890		 Mailing Address:
Department of ECE, Carnegie Mellon University,
5000 Forbes Avenue, Pittsburgh,
PA 15213-3890

[Research Interests]   [Research]  [Downloads]   [Recent Publications]   [Talks]

Research Interests

My research interests are in pattern recognition and machine learning with specific interests in their application to biometric learning and classification along with the combination of biometrics stemming from multiple modalities. I have been specifically developing state of the art face and voice verification algorithms by employing generative models and theories on generalization in pattern recognition and Bayesian adaptation. I have also been attacking the problem of obtaining synergetic combination for an ensemble of pattern recognizing classifiers. I am welled versed in many aspects of pattern recognition and biometrics, and am extremely interested in how developments in these areas can improve and develop our knowledge of broader problems in artificial intelligence (AI).

Research

Should we make automatic PR more human? - The Pattern Recognition (PR) community is largely split on whether it is a good or bad thing to try and make (and how) automatic PRs mimic humans. The central vision for much of our research is concerned with an answer to such a question.

Face Recognition - We have been actively pursuing algorithms for more human like face recognition in terms of the ability to generalize to unseen conditions and employing different representations for different claimants.
Voice Recognition - The ability to estimate robust and accurate speaker models with modest amounts of training utterances is still an elusive task. We are actively developing techniques to address this important problem.
Multimodal Biometrics - The synergetic fusion of multiple biometric traits has been shown to be of benefit in the detection of fraud and improving the performance and robustness of existing biometric technologies. 

Downloads (FHI - Library) and Links

Recently a lot of our research has been concentrating on developing accurate and robust Free-parts and Holistic Integration (FHI) algorithm [Lucey&Chen04, Lucey&Chen05]. Based on this work we have produced a suite of scripts for batch processing and analysis (mainly in MATLAB and BASH). We have also produced a FHI C++ library suitable for real-time and prototype development.

[Link to downloads]

Most of this code has been developed from the OpenCV computer vision library and a great machine learning library I use called Torch. I would encourage anyone active in the area of biometrics or pattern recognition to check out these great tools.

Students

I am currently co-supervising the following students,

  • Nisarg Vyas - Master's Student (Face Recognition/Detection in Compression)
  • Mike Beattie - Ph.D. Student (Mult-modal Biometrics)

Recent talks

  • "A Tutorial on Speaker Verification" presented at Sony, San Jose, 5th-6th September 2002. [ppt]
  • "Towards Habile Face Recognition", presented at the Australian National University (ANU), Canberra, Australia on January 17th 2005. [ppt]

Recent publications

  • S. Lucey and T. Chen, "Integrating Monolithic and Free-parts Representations for Improved Face Verification in the Presence of Pose Mismatch", [technical report], October 2004.
  • S. Lucey and C. Sanderson, "Synthesized GMM Free-parts Based Face Representation for Pose Mismatch Reduction in Face Verification", [technical report], October 2004.
  • M. Beattie, B.V.K. Vijaya Kumar, S. Lucey, and O. Tonguz. Building access control using coordinated biometric verification. Biometrics: Challenges arising from Theory to Practice workshop (BCTP), Cambridge, U.K. 2004.
  • S. Lucey, "The symbiotic relationship of parts and monolithic face representations in verification," presented at International Workshop on Face Processing in Video (FPIV), Washington D.C., 2004. [similar technical report]
  • S. Lucey and T. Chen, "A GMM parts based face representation for improved verification through relevance adaptation," presented at International Conference on Computer Vision and Pattern Recognition (CVPR), Washington D.C., 2004. [similar technical report]
  • S. Lucey, T. Chen, S. Sridharan, and V. Chandran, "Integration strategies for audio-visual speech processing: Applied to text
    dependent speaker recognition," IEEE Trans. on Multimedia, 2005. [similar technical report]
  • S. Lucey, "An evaluation of visual speech features for the tasks of speech and speaker recognition," presented at International Conference of Audio- and Video-Based Person Authentication (AVBPA), pp. 260-267, Guildford, U.K., 2003. [similar technical report]
  • S. Lucey and T. Chen, "Improved audio-visual speaker recognition via the use of a hybrid combination strategy," presented at International Conference of Audio- and Video-Based Person Authentication (AVBPA), pp. 929-936, Guildford, U.K., 2003. [similar technical report]
  • S. Lucey and T. Chen, "An investigation into subspace rapid speaker adaptation for verification," presented at IEEE Conference on Multimedia and Expo (ICME), pp. 69-72, Baltimore MD, U.S.A., 2003. [similar technical report]
  • S. Lucey and T. Chen, "Improved speaker verification through probabilistic subspace adaptation," presented at Eurospeech, pp. 2021-2024, Geneva, Switzerland, 2003. [similar technical report]
  • S. Lucey, S. Sridharan, and V. Chandran, "Improved facial feature detection for AVSP via unsupervised clustering and discriminant analysis," EURASIP Journal on Applied Signal Processing, pp. 264-275, 2003. [similar technical report]
  • S. Lucey and S. Sridharan, "A theoretical framework for independent classier combination," presented at International Conference on Pattern Recognition (ICPR), Quebec City, Canada, 2002. [similar technical report]
  • S. Lucey, S. Sridharan, and V. Chandran, "A link between cepstral shrinking and the weighted product rule in audio-visual speech recognition," presented at International Conference on Spoken Language Processing (ICSLP), pp. 1961-1964, Denver, Colorado, 2002. [similar technical report]
  • S. Lucey, S. Sridharan, and V. Chandran, "Adaptive mouth segmentation using chromatic features," Pattern Recognition Letters, vol. 23, pp. 1293-1302, 2002. [similar technical report]
  • S. Lucey, S. Sridharan, and V. Chandran, "An investigation of HMM classifier combination strategies for improved audio-visual speech recognition," presented at Eurospeech, pp. 1185-1188, Aalborg, Denmark, 2001. [similar technical report]
  • S. Lucey, S. Sridharan, and V. Chandran, "A suitability metric for mouth tracking through chromatic segmentation," presented at International Conference on Image Processing (ICIP), pp. 258-261, Thessaloniki, Greece, 2001. [similar technical report]

   [Link to all publications]

Top of this page

Last updated 17th February, 2005