Research

Eric Patterson, Ph.D.

 

Current Interests:

Automatic Facial Aging of 2-D Images and 3-D Models

The human face is extremely important to the way we communicate with and identify each other. Because of its importance and our familiarity with it, the face is a very challenging subject of research and involves many areas such as 3-D modeling and animation of the face, representation of the face for communication, and identification of the face. As a person ages, many factors change in the face, yet we as humans still identify and communicate very effectively. Even minor changes in the face, however, provide a significant challenge to current computer technology for facial representation, tracking, and recognition. An interdisciplinary team here at UNCW is currently investigating ways to qualify and quantify these changes to aid in the many areas of facial research across fields.

Emotion Recognition and Performance-Driven Facial Animation

One's face is constantly, even unconsciously, performing expressions and micro-expressions that convey additional semantic information and clues to the emotional state of the person. Recognizing and using the information conveyed by these expressions has the potential to enhance user interface applications and also drive other technologies such as performance-driven facial animation.

Audio-Visual Speech Recognition

Automatic speech recognition technologies have progressed significantly with the advanced power of modern computers. Systems are still subject to many constraints, however, such as limited vocabulary, single-speaker use, and intolerance of background noise. A multimodal approach to speech recognition which combines video "lip-reading" along with traditional audio-signal processing has the potential to overcome many of these challenges as well as improve the intuitive nature of man-machine interfaces.

Link to the Face Aging Group at UNCW.

Link to a recent news segment that discusses our interdisciplinary research on facial aging. (MPEG format. Quicktime may be necessary.)

Links to Selected Papers:

E. Patterson, A. Sethuram, K. Ricanek, and F. Bingham, "Improvements in Active Appearance Model Based Synthetic Age Progression for Adult Aging," Proceedings of the IEEE Conference on Biometrics: Theory, Applications, and Systems, Washington, D.C., September, 2009.

M. Ratliff and E. Patterson, "Emotion Recognition Using Facial Expressions with Active Appearance Models," Proceedings of the IASTED International Conference on Human-Computer Interface, Innsbruck, March, 2008.

E. Patterson, A. Sethuram, M. Albert, K. Ricanek, and M. King, "Aspects of Age Variation in Facial Morphology Affecting Biometrics," Proceedings of the IEEE Conference on Biometrics: Theory, Applications, and Systems, Washington, D.C., September, 2007.

E. Patterson, A. Sethuram, M. Albert, and K. Ricanek, "Comparison of Synthetic Face Aging to Age Progression by Forensic Sketch Artist," Proceedings of the IASTED International Conference on Visualization, Imaging, and Image Processing, Palma de Mallorca, Spain, August, 2007.

K. Ricanek, R. Wilkins, A. Sethuram, and E. Patterson, "A Novel Cognitive-Psychology-Based Face-Recognition System for Improved Identification Rates for the Problem of Age-Progressions," Proceedings of the IASTED International Conference on Visualization, Imaging, and Image Processing, Palma de Mallorca, Spain, August, 2007.

A.M Albert, K. Ricanek, and E. Patterson, "A Review of the Literature on the Aging Adult Skull and Face: Implications for Forensic Science Research and Applications," Forensic Science International, October, 2007.

Z. Tufekci, J. Gowdy, S. Gurbuz, and E. Patterson, "Applied Mel-Frequency Discrete Wavelet Coefficients and Parallel Model Compensation for Noise-Robust Speech Recognition," Speech Communication, Elsevier, October, 2006.

E. Patterson, K. Ricanek, M. Albert, and E. Boone, "Automatic Representation of Adult Aging in Facial Images," IASTED International Conference on Visualization, Imaging, and Image Processing, Palma de Mallorca, Spain, August, 2006.

E.K. Patterson and J.N. Gowdy, “An Audio-Visual Approach to Simultaneous-Speaker Speech Recognition,” Proceedings of the IEEE International Conference on Acoustics,Speech, and Signal Processing, Hong Kong, April 2003.

J.N. Gowdy, E.K. Patterson, D. Wu, and S. Niska, “Development and Use of Simulation Models for Teaching a Distance-Learning Course on Digital Processing of Speech Signals,” Proceedings of the e-Technologies in Engineering Education Conference, Switzerland, August, 2002.

E.K. Patterson, S. Gurbuz, Z. Tufekci, and J.N. Gowdy, “Moving-Talker, Speaker-Independent Feature Study and Baseline Results using the CUAVE Multimodal Speech Corpus,” EURASIP Journal on Applied Signal Processing, December 2002.

E.K. Patterson and J.N. Gowdy, “Experiments Using the CUAVE Audio-Visual Speech Corpus in Rotation and Scale Correction of Visual Speech Features,” DARPA Workshop on Multi-Modal Speech Recognition, Greensboro, NC, June 2002.

E.K. Patterson, S. Gurbuz, Z. Tufekci, and J.N. Gowdy, “CUAVE: A New Audio-Visual Database for Multimodal Human-Computer Interface Research,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Orlando, May 2002.

E.K. Patterson, S. Gurbuz, Z. Tufekci, and J.N. Gowdy, “Noise-Based Audio-Visual Fusion for Robust Speech Recognition,” International Conference on Auditory-Visual Speech Processing, Scheelsminde, Denmark, September 2001.

E.K. Patterson and J.N. Gowdy, “Modeling Speech-Interfering Noise with Applied Chaos Theory,” I.E.E.E. Southeastern Conference, March 2001.

E.K. Patterson, J.N. Gowdy, and D. Wu, “Multi-Platform CBI Tools Using Linux and Java-Based Solutions for Distance Learning,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Seattle, May 1998.

Other useful Links :

Link to UNCW Library's Computer Related Databases.

Link to Face Recognition Algorithms.