Mission

The Face Group conducts applied research in Face Analysis/Synthesis and Biometric Technologies as well as basic research in Pattern Recognition and Machine Learning. The applied research is aimed to develop technologies for face modeling, analysis and synthesis aimed at automated face detection, recognition, and rendering; and to make the algorithms work fast and robustly in practical applications. The basic research is aimed to understand fundamental problems in data analysis and information processing, so as to provide theoretical bases for developing pattern recognition and machine learning techniques and algorithms for modeling, analysis, classification and synthesis of real world image, video, and audio data.

Project Overview

Face Technologies This project is aimed to develop techniques and algorithms for automated face recognition. The research topics include detection, tracking, pose estimation, alignment, and recognition of multi-view faces, where multi-view means reasonable amount of in-plane, out-of-plane and up-down rotations. The structure of the current system is shown in the figure below. The system takes gray level static images or video as the input, without using color or motion information, and finds the locations, sizes, poses of faces in the input, and recognize their identities; all these are done in real-time. The system also includes internal feedback mechanisms for collecting and adding to the training sets new face examples for re-training the performing modules. Our objective is to make these components work practically, fast and robustly.  See more details here.

Subspace Learning This project is aimed to understand fundamental problems in pattern analysis and classification, and to develop new learning techniques and algorithms for modeling and classification of real world image, video, audio and speech data. The basic issues are: (1) understanding intrinsically low-dimensional structures or sub-manifolds of patterns of interest embedded in high dimensional data, and (2) discriminating between different patterns. The topics include linear and nonlinear subspace learning, example-based learning, statistical and neural network methods for modeling and classification. See more details here.

Windows Biometrics (WinBM).  This project is aimed to develop biometric technologies for (1) secured Windows environment at the platform level, and interoperability between different biometric applications, and (2) development of reliable biometric technologies and applications. WinBM provides biometrics interfaces with the Windows platform following the Next-Generation Secure Computing Base (NGSCB) secure input specification. The interoperability makes it convenient and versatile to integrate into the Windows various biometrics applications for person identification and verification,  including face, iris, speaker, signature and fingerprint, and smartcard for logon. Different levels of security and usability are supported in a unified WinBM framework in order to cater to different needs, such as Home/Standalone, Government/Enterprise, Tablet PC, and mobiles. See more details here.

Group Pictures

A multi-view face picture taken on Sep 14, 2001, and face detection result.

At the launch of EyeCU-II system for Face and Iris Based Recognition and Security, Feb 19, 2003.

On completion of  EyeCU-II-plus, Sep 1, 2003.