Conference paper
Nose Tip Detection on a Three-Dimensional Face Range Image Invariant to Head Pose
IMECS 2009: International MultiConference of Engineers and Computer Scientists 2009 Proceedings; Volumes I and II, pp.858-862
International MultiConference of Engineers and Computer Scientists , 2009 (18-Mar-2009 - 20-Mar-2009)
Newswood Limited
2009
Abstract
Nose detection is an important part of a 3D face recognition process. Knowledge of the nose location will enable us to align an unknown 31) face with those in a face database. Besides that, the head pose can be deduced from information obtained from the nose. this paper, a method is proposed to detect the nose tip from a (three-dimensional face range image. This method identifies potential nose tip candidates by investigating the surrounding pixels. The nose tip is then identified from the potential candidates by their mean and variance values as well as (their location which must be within the nose area. The proposed method has the ability to locate the nose tip without any manual input from the user, requires no training and is able to locate the nose tip for faces at different angles.
Details
- Title
- Nose Tip Detection on a Three-Dimensional Face Range Image Invariant to Head Pose
- Authors
- Wei Jen Chew (Author) - University of NottinghamKah Phooi Seng (Author) - University of NottinghamLi-Minn Ang (Author) - University of Nottingham
- Contributors
- Sio-Iong Ao (Editor) - International Association of EngineersOscar Castillo (Editor) - Instituto Tecnológico de TijuanaCraig Douglas (Editor)David Dagan Feng (Editor)Jeong A Lee (Editor)
- Publication details
- IMECS 2009: International MultiConference of Engineers and Computer Scientists 2009 Proceedings; Volumes I and II, pp.858-862
- Conference details
- International MultiConference of Engineers and Computer Scientists , 2009 (18-Mar-2009 - 20-Mar-2009)
- Publisher
- Newswood Limited
- Organisation Unit
- University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; Engage Research Lab
- Language
- English
- Record Identifier
- 99642375702621
- Output Type
- Conference paper
Metrics
37 Record Views