Paper Info
Title
Merging and arbitration strategy applied bayesian classification for eye location
Abstract
Based on template facial features and image segmentation, this paper demonstrates a novel method for automatic detection of eyes in grayscale still images. A decision model of eye location is instituted by the priori knowledge of template facial features. After roughly detection of face, we apply three steps for system to locate eyes. Firstly, the Bayesian eye detector is used to find eye patterns in the upper region of the face image. This vector based Bayesian classifier adopts Haar transform as vectorize because we know that is robust at illumination variation. Secondly, merging and arbitration strategy are applied. It can manage variations of around eye regions due to spectacle rims or eye brows. Finally, Gaussian-projection function can locate robust precision eye position. The experimental results show that the proposed method can achieve higher performance at any test data.
Year
DOI
Venue
2006
10.1007/11815921_97
SSPR/SPR
Keywords
Field
DocType
bayesian classification,template facial feature,face image,automatic detection,bayesian classifier,eye pattern,bayesian eye detector,robust precision eye position,eye location,eye brow,eye region,arbitration strategy,image segmentation,decision models
Computer vision,Facial recognition system,Naive Bayes classifier,Computer science,Image segmentation,Mahalanobis distance,Artificial intelligence,Face detection,Luminance,Grayscale,Bayesian probability
Conference
Volume
ISSN
ISBN
4109
0302-9743
3-540-37236-9
Citations 
PageRank 
References 
0
0.34
11
Authors
2
Name
Order
Citations
PageRank
Eun Jin Koh132.46
Phill Kyu Rhee26024.82