Face recognition from unfamiliar views: subspace methods and pose dependency
- 14 April 1998
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 348-353
- https://doi.org/10.1109/afgr.1998.670973
Abstract
A framework for recognising human faces from unfamiliar views is described and a simple implementation of this framework evaluated. The interaction between training view and testing view is shown to compare with observations in human face recognition experiments. The ability of the system to learn from several training views, as available in video footage, is shown to improve the overall performance of the system as is the use of multiple testing imageKeywords
This publication has 12 references indexed in Scilit:
- Face recognition from one example viewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- What Represents a Face? A Computational Approach for the Integration of Physiological and Psychological DataPerception, 1997
- Can a linear autoassociator recognize faces from new orientations?Journal of the Optical Society of America A, 1996
- Face Tracking and Pose RepresentationPublished by British Machine Vision Association and Society for Pattern Recognition ,1996
- Linear Object Classes and Image Synthesis from a Single Example Image.Published by Defense Technical Information Center (DTIC) ,1995
- View-based and modular eigenspaces for face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Three-dimensional face model reproduction method using multiview imagesPublished by SPIE-Intl Soc Optical Eng ,1991
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991
- Fast Learning in Networks of Locally-Tuned Processing UnitsNeural Computation, 1989
- When face recognition fails.Journal of Experimental Psychology: Human Learning and Memory, 1977