Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

Face detection and clustering for video indexing applications

Czirjek, Csaba and O'Connor, Noel E. and Marlow, Seán and Murphy, Noel (2003) Face detection and clustering for video indexing applications. In: ACIVS 2003 - Advanced Concepts for Intelligent Vision Systems, 2-5 September 2003, Ghent, Belgium.

Full text available as:

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


This paper describes a method for automatically detecting human faces in generic video sequences. We employ an iterative algorithm in order to give a confidence measure for the presence or absence of faces within video shots. Skin colour filtering is carried out on a selected number of frames per video shot, followed by the application of shape and size heuristics. Finally, the remaining candidate regions are normalized and projected into an eigenspace, the reconstruction error being the measure of confidence for presence/absence of face. Following this, the confidence score for the entire video shot is calculated. In order to cluster extracted faces into a set of face classes, we employ an incremental procedure using a PCA-based dissimilarity measure in con-junction with spatio-temporal correlation. Experiments were carried out on a representative broadcast news test corpus.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Subjects:Computer Science > Digital video
Computer Science > Information retrieval
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Digital Video Processing (CDVP)
Publisher:Acivs 2003
Official URL:
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:EU IST-2000-32795, Enterprise Ireland
ID Code:341
Deposited On:13 Mar 2008 by DORAS Administrator. Last Modified 07 May 2010 11:11

Download statistics

Archive Staff Only: edit this record