Vuong Le

Email: vuongle2 (at) (or)


My technical interest is on the range of image and video processing, machine learning and computer vision. I have been especially invested my time in building models and algorithms to accurately recognize 3D shapes and motions from RGB-D signals. Applications of these works include animation and biometrics such as detecting and recognizing human emotions and actions in images and videos. Recently I am more involved with object detection and recognition in industrial camera systems.

I secured a PhD of Department of Electrical and Computer Engineering, University of Illinois at Urbana Champaign in 2014.  I am currently with Amazon in Seattle on an undisclosed project. We are working on a distributed system using a wide range of computer vision and image processing techniques in an initiative aiming at providing unique customer experience.



·        June 2016: Our Patent with HP “3D modeling motion parameters” is granted.

·        March 2016: Our book “Face Processing and Applications to Distance Learning” is on the shelves! Check it out:

·        December 2015: Two more patents granted: “Adjusting a contour by a shape model” and “Fitting contours to features

Past Projects

3D face processing for animation and biometrics (funded by Intel, Microsoft, Cisco)

Avacholar - Visual Applications Framework in Immersive Virtual Educational Environments

Interactive face segmentation for portrait editing and Helen dataset (with Adobe)

Facial shape representation based on facial level curves from depth images for emotion recognition with Hidden Markov Model.

Cloud-based simultaneous localization and mapping (SLAM) for reconstruction of 3D scenes using RGB-D data (with HP labs)

A Wavelet Approach for Cellular Optical Phase Shift Data Analysis


Fast scalable multi-pole algorithm for efficient fitting of RBF implicit embedding to the noisy scattered 3D point cloud.


Human action recognition classifier using shape features


·         3D modeling motion parameters. Vuong Le, Wei Hong, Kar-Han Tan, John Apostolopoulos – 2016, US Patent 9,286,717

·         Adjusting a contour by a shape model. Jonathan W. Brandt, Zhe Lin, Vuong Le, Lubomir D. Bourdev – 2015, US Patent 9,202,138

·         Fitting contours to features. Jonathan W. Brandt, Zhe Lin, Lubomir D. Bourdev, Vuong Le – 2015, US Patent 9,158,963

·         Methods and Apparatus for Automated Portrait Retouching Using Facial Feature Localization. Jonathan Brandt, Zhe Lin, Vuong Le – 2014, US Patent 8,811,686

·         Methods and Apparatus for Automated Facial Feature Localization. Jonathan Brandt, Zhe Lin, Vuong Le – 2014, US Patent 8,824,808

Books & book chapters

·         Vuong Le, Usman Tariq, Pooya Khorrami, Hao Tang, Thomas S. Huang, Face processing and Applications to Distance Learning, World Scientific Publishing Company, 2016.  Monograph, ISBN: 9789814733021

·         Dennis Lin, Vuong Le, Thomas S. Huang, Human-Computer Interaction (Book chapter), in Visual Analysis of Humans: Looking at People, Springer 2011


·         Antoni  Liang, Wanquan Liu, Ling Li, Mir Rizwan Farid, Vuong Le, Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models. ICPR 2014

·         Thomas Huang, Vuong Le, Thomas Paine, Pooya Khorrami, Usman Tariq, Visual Media: History and Perspectives, IEEE Multimedia, April - June 2014

·         Pooya Khorrami, Vuong Le, John C. Hart, Thomas S. Huang: A System for Monitoring the Engagement of Remote Online Students, ICMEWorkshop 2014

·         Vuong Le, Jonathan Brandt, Lubomir Boudev, Zhe Lin, Thomas S. Huang, Interactive Facial Feature Localization, European conference on computer vision ECCV 2012

·         Vuong Le, Hao Tang, Thomas S. Huang, Expression Recognition from 3D Dynamic Faces using Robust Spatio-temporal Shape Features, International Conference on Automatic Face and Gesture Recognition – FGR 2011

·         Usman Tariq, Kai-Hsiang Lin, Zhen Li, Xi Zhou, Zhaowen Wang, Vuong Le, Thomas S. Huang, Xutao Lv, Tony X. Han: Emotion recognition from an ensemble of features - FGR 2011

·         Vuong Le, Hao Tang, Liangliang Cao, Thomas S. Huang, Accurate and Efficient Reconstruction of 3D Faces From Stereo Images, IEEE International Conference on Image Processing 2010 -ICIP 2010

·         Vuong Le, Yuxiao Hu, Thomas S. Huang, A Quantitative Evaluation for 3D Face Reconstruction Algorithms, IEEE International Conference on Acoustics, Speech, and Signal Processing 2009 - ICASSP 2009

·         Mert Dikmen, Huazhong Ning, Dennis J. Lin, Liangliang Cao, Vuong Le, Shen-Fu Tsai, Kai-Hsiang Lin, Zhen Li, Jianchao Yang, Thomas S. Huang, Fengjun Lv, Wei Xu, Ming Yang, Kai Yu, G. Zhu, Yihong Gong, Surveillance Event Detection, TRECVID 2008