Pose-invariant face recognition with parametric linear subspaces
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We present a framework for pose-invariant face recognition using parametric linear subspace models as stored representations of known individuals. Each model can be fit to an input, resulting in faces of known people whose head pose is aligned to the input face. The model's continuous nature enables the pose alignment to be very accurate, improving recognition performance, while its generalization to unknown poses enables the models to be compact. Recognition systems with two types of parametric linear model are compared using a database of 20 persons. The results showed our system's robust recognition of faces with /spl plusmn/50 degree range of full 3D head rotation, while compressing the data by a factor of 20 and more.Keywords
This publication has 13 references indexed in Scilit:
- Analysis and synthesis of human faces with pose variations by a parametric piecewise linear subspace methodPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Tracking and learning graphs and pose on image sequences of facesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Face recognition from one example viewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Analysis and synthesis of pose variations of human faces by a linear PCMAP model and its application for pose-invariant face recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- SFS based view synthesis for robust face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The FERET evaluation methodology for face-recognition algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Constructive Incremental Learning from Only Local InformationNeural Computation, 1998
- Face recognition by elastic bunch graph matchingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Visual learning and recognition of 3-d objects from appearanceInternational Journal of Computer Vision, 1995
- View-based and modular eigenspaces for face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994