Maximum variance projections for face recognition
Authors:
- Deli ZhaoDZDeli Zhao
- 1 June 2007
- journal article
- Published by SPIE-Intl Soc Optical Eng in Optical Engineering
- Vol. 46 (6) , 067206-067206-8
Abstract
Maximum variance projection (MVP), as a novel subspace learning algorithm, is proposed. It is a linear discriminant algorithm that preserves local information by capturing the local geometry of the manifold. Two abilities of manifold learning and classification are combined into the properties of our algorithm. Since face images often belong to a submanifold of intrinsically low dimension, we carry out the MVP algorithm for face manifold learning and classification. Several experiments show the effectiveness of our developed algorithm.Keywords
This publication has 18 references indexed in Scilit:
- Linear local tangent space alignment and application to face recognitionNeurocomputing, 2007
- Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space AlignmentSIAM Journal on Scientific Computing, 2004
- Face recognitionACM Computing Surveys, 2003
- PCA versus LDAIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- A Global Geometric Framework for Nonlinear Dimensionality ReductionScience, 2000
- Eigenfaces vs. Fisherfaces: recognition using class specific linear projectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Using discriminant eigenfeatures for image retrievalIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Human and machine recognition of faces: a surveyProceedings of the IEEE, 1995
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991