Cs Colloquium 2

Automated face recognition at CSU and at Large
Ross Beveridge, Computer Science Department, CSU

In this talk, Professor Beveridge summarized his research in the area of automated face recognition. At the beginning, Professor Beveridge briefly introduced the automated face recognition technology, including: parts and types of face recognition, application of face recognition technology and criterion of face recognition. Meanwhile, large scale independent evaluations for face recognition systems, The Face Recognition Vendor Test (FRVT) 2006, was introduced.

After that, Professor Beveridge introduced some face recognition algorithms, which are implemented in The CSU Face Identification Evaluation System, like Elastic Bunch Graph Matching (EBGM). The algorithm of Elastic Bunch Graph Matching recognizes novel faces by first localizing a set of landmark features and then measuring similarity between these features. The CSU Face Identification Evaluation System provides standard face recognition algorithms and standard statistical methods for comparing face recognition algorithms. The system includes standardized image pre-processing software, three distinct face recognition algorithms, analysis software to study algorithm performance, and Unix shell scripts to run standard experiments.

Professor Beveridge mentioned his five papers about his face recognition research in CSU. From these papers, we can learn some topics in face cognition area, like some factors influence algorithm performance, illumination face space, face detection algorithm and person identification using both text and image data.

Last modified 25 November 2007 at 10:44 pm by yifei