Visual object recognition with bagging of one class support vector machines

Zongxia Xie; Yong Xu; Qinghua Hu

doi:10.1109/IBICA.2011.29

Visual object recognition with bagging of one class support vector machines

Zongxia Xie^*
, Yong Xu
, Qinghua Hu

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

Abstract

A large number of training samples is requiredin developing visual object recognition systems. However, the size of samples is limited sometimes. This paper investigates bagging of one class support vector machines (OCSVM), which just use one class of objects for training. Experiments are performed on Caltech101 database. Our findings show that the performance with bagging method is better than single OCSVM. Furthermore, bagging of OCSVM can also keep better performance with limited number of training samples.

Original language	English
Pages	99-102
Number of pages	4
DOIs	https://doi.org/10.1109/IBICA.2011.29
State	Published - 2011
Externally published	Yes
Event	2011 2nd International Conference on Innovations in Bio-inspired Computing and Applications, IBICA 2011 - Shenzhen, Guangdong, China Duration: 16 Dec 2011 → 18 Dec 2011

Conference

Conference	2011 2nd International Conference on Innovations in Bio-inspired Computing and Applications, IBICA 2011
Country/Territory	China
City	Shenzhen, Guangdong
Period	16/12/11 → 18/12/11

Keywords

bagging
one class support vector machines
visual boject recognition

Access to Document

10.1109/IBICA.2011.29

Cite this

@conference{54c333cb93734d858f602388b838aae7,

title = "Visual object recognition with bagging of one class support vector machines",

abstract = "A large number of training samples is requiredin developing visual object recognition systems. However, the size of samples is limited sometimes. This paper investigates bagging of one class support vector machines (OCSVM), which just use one class of objects for training. Experiments are performed on Caltech101 database. Our findings show that the performance with bagging method is better than single OCSVM. Furthermore, bagging of OCSVM can also keep better performance with limited number of training samples.",

keywords = "bagging, one class support vector machines, visual boject recognition",

author = "Zongxia Xie and Yong Xu and Qinghua Hu",

year = "2011",

doi = "10.1109/IBICA.2011.29",

language = "英语",

pages = "99--102",

note = "2011 2nd International Conference on Innovations in Bio-inspired Computing and Applications, IBICA 2011 ; Conference date: 16-12-2011 Through 18-12-2011",

}

TY - CONF

T1 - Visual object recognition with bagging of one class support vector machines

AU - Xie, Zongxia

AU - Xu, Yong

AU - Hu, Qinghua

PY - 2011

Y1 - 2011

N2 - A large number of training samples is requiredin developing visual object recognition systems. However, the size of samples is limited sometimes. This paper investigates bagging of one class support vector machines (OCSVM), which just use one class of objects for training. Experiments are performed on Caltech101 database. Our findings show that the performance with bagging method is better than single OCSVM. Furthermore, bagging of OCSVM can also keep better performance with limited number of training samples.

AB - A large number of training samples is requiredin developing visual object recognition systems. However, the size of samples is limited sometimes. This paper investigates bagging of one class support vector machines (OCSVM), which just use one class of objects for training. Experiments are performed on Caltech101 database. Our findings show that the performance with bagging method is better than single OCSVM. Furthermore, bagging of OCSVM can also keep better performance with limited number of training samples.

KW - bagging

KW - one class support vector machines

KW - visual boject recognition

UR - https://www.scopus.com/pages/publications/84862960049

U2 - 10.1109/IBICA.2011.29

DO - 10.1109/IBICA.2011.29

M3 - 论文

AN - SCOPUS:84862960049

SP - 99

EP - 102

T2 - 2011 2nd International Conference on Innovations in Bio-inspired Computing and Applications, IBICA 2011

Y2 - 16 December 2011 through 18 December 2011

ER -

Visual object recognition with bagging of one class support vector machines

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this