Rule based segmentation and subject identification using fiducial features and subspace projection methods
Author
Ince, E. A.
Ali, S. A.
Date
2007Source Title
Journal of Computers
Print ISSN
1796-203X
Publisher
Academy Publisher
Volume
2
Issue
4
Pages
68 - 75
Language
English
Type
ArticleItem Usage Stats
115
views
views
79
downloads
downloads
Abstract
This paper describes a framework for carrying out face recognition on a subset of standard color FERET database using two different subspace projection methods, namely PCA and Fisherfaces. At first, a rule based skin region segmentation algorithm is discussed and then details about eye localization and geometric normalization are given. The work achieves scale and rotation invariance by fixing the inter ocular distance to a selected value and by setting the direction of the eye-to-eye axis. Furthermore, the work also tries to avoid the small sample space (S3) problem by increasing the number of shots per subject through the use of one duplicate set per subject. Finally, performance analysis for the normalized global faces, the individual extracted features and for a multiple component combination are provided using a nearest neighbour classifier with Euclidean and/or Cosine distance metrics.
Keywords
Color FERET databaseFeature extraction
Geometric normalization
Skin color segmentation
Subspace analysis methods
Distance metrics
Euclidean
Eye localization
FERET database
Fisher-faces
Geometric normalization
Multiple components
Nearest-neighbour classifier
Number of shots
Performance analysis
Region segmentation
Rule based
Scale and rotation
Skin-color segmentation
Small samples
Subject identification
Subspace analysis
Subspace projection methods
Feature extraction
Face recognition