Paper Info
Title
2D Cascaded AdaBoost for Eye Localization
Abstract
In this paper, 2D cascaded AdaBoost, a novel classifier designing framework, is presented and applied to eye localization. By the term "2D", we mean that in our method there are two cascade classifiers in two directions: The first one is a cascade designed by bootstrapping the positive samples, and the second one, as the component classifiers of the first one, is cascaded by bootstrapping the negative samples. The advantages of the 2D structure include: (1) it greatly facilitates the classifier designing on huge-scale training set; (2) it can easily deal with the significant variations within the positive (or negative) samples; (3) both the training and testing procedures are more efficient. The proposed structure is applied to eye localization and evaluated on four public face databases, extensive experimental results verified the effectiveness, efficiency, and robustness of the proposed method
Year
DOI
Venue
2006
10.1109/ICPR.2006.1194
ICPR (2)
Keywords
Field
DocType
classifier designing framework,component classifier,2d cascaded adaboost,face recognition,negative sample,cascade classifier,cascaded adaboost,learning (artificial intelligence),novel classifier,eye localization,pattern classification,huge-scale training set,positive sample,proposed structure,pattern recognition,robustness,face detection,testing,learning artificial intelligence,computer science,computer vision,machine vision
Bootstrapping,Computer science,Robustness (computer science),Artificial intelligence,Classifier (linguistics),Training set,Computer vision,Facial recognition system,AdaBoost,Pattern recognition,Cascading classifiers,Cascade,Machine learning
Conference
Volume
ISSN
ISBN
2
1051-4651
0-7695-2521-0
Citations 
PageRank 
References 
58
2.28
12
Authors
5
Name
Order
Citations
PageRank
Zhiheng Niu1824.46
Shiguang Shan26322283.75
Shengye Yan31509.25
Xilin Chen46291306.27
Wen Gao511374741.77