QUT QUT ePrints

Improved Facial-Feature Detection for AVSP via Unsupervised Clustering and Discriminant Analysis

Lucey, Simon and Sridharan, Sridha and Chandran, Vinod (2003) Improved Facial-Feature Detection for AVSP via Unsupervised Clustering and Discriminant Analysis. EURASIP Journal on Applied Signal Processing 2003(3):pp. 264-275.

Full text available as:
PDF - Requires Adobe Acrobat Reader or other PDF viewer.

Abstract

An integral part of any audio-visual speech processing (AVSP) system is the front-end visual system that detects facial-features (e.g., eyes and mouth) pertinent to the task of visual speech processing. The ability of this front-end system to not only locate, but also give a confidence measure that the facial-feature is present in the image, directly affects the ability of any subsequent post-processing task such as speech or speaker recognition. With these issues in mind, this paper presents a framework for a facial-feature detection system suitable for use in an AVSP system, but whose basic framework is useful for any application requiring frontal facial-feature detection. A novel approach for facial-feature detection is presented, based on an appearance paradigm. This approach, based on intraclass unsupervised clustering and discriminant analysis, displays improved detection performance over conventional techniques.

Item Type:Journal Article
RM Number:2004001664
Status:Published
Keywords:audio-visual speech processing, facial-feature detection, unsupervised clustering, discriminant analysis
Subjects:Subjects UNSPECIFIED
ID Code:10093
Deposited By:Bozzetto, Adam
Deposited On:11 October 2007
Alternative Locations:http://dx.doi.org/10.1155/S1110865703209045
Copyright Owner:Copyright 2003 (The authors)
Additional Information:The contents of this journal can be freely accessed online via the journal’s web page (see hypertext link).