Learning based on kernel discriminant-em algorithm for image classification

Qi Tian, Jie Yu, Ying Wu, Thomas S. Huang

Research output: Contribution to journalConference article

Abstract

In image classification and other learning-based object recognition tasks, it is often tedious and expensive to label large training data sets. Discriminant-EM (DEM) proposed a semi-supervised learning framework which takes both labeled and unlabeled data to learn classifiers. This paper extends the linear D-EM to nonlinear kernel algorithm, KDEM and evaluates KDEM on both benchmark image databases and synthetic data. Various comparisons with other state-of-the-art learning techniques are investigated.

Original languageEnglish (US)
Pages (from-to)V-461-V-464
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume5
StatePublished - Sep 27 2004
EventProceedings - IEEE International Conference on Acoustics, Speech, and Signal Processing - Montreal, Que, Canada
Duration: May 17 2004May 21 2004

Fingerprint

Image classification
Supervised learning
Object recognition
Labels
Classifiers

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Learning based on kernel discriminant-em algorithm for image classification. / Tian, Qi; Yu, Jie; Wu, Ying; Huang, Thomas S.

In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 5, 27.09.2004, p. V-461-V-464.

Research output: Contribution to journalConference article

@article{8d5985b766514918990af234f0685139,
title = "Learning based on kernel discriminant-em algorithm for image classification",
abstract = "In image classification and other learning-based object recognition tasks, it is often tedious and expensive to label large training data sets. Discriminant-EM (DEM) proposed a semi-supervised learning framework which takes both labeled and unlabeled data to learn classifiers. This paper extends the linear D-EM to nonlinear kernel algorithm, KDEM and evaluates KDEM on both benchmark image databases and synthetic data. Various comparisons with other state-of-the-art learning techniques are investigated.",
author = "Qi Tian and Jie Yu and Ying Wu and Huang, {Thomas S.}",
year = "2004",
month = "9",
day = "27",
language = "English (US)",
volume = "5",
pages = "V--461--V--464",
journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
issn = "0736-7791",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Learning based on kernel discriminant-em algorithm for image classification

AU - Tian, Qi

AU - Yu, Jie

AU - Wu, Ying

AU - Huang, Thomas S.

PY - 2004/9/27

Y1 - 2004/9/27

N2 - In image classification and other learning-based object recognition tasks, it is often tedious and expensive to label large training data sets. Discriminant-EM (DEM) proposed a semi-supervised learning framework which takes both labeled and unlabeled data to learn classifiers. This paper extends the linear D-EM to nonlinear kernel algorithm, KDEM and evaluates KDEM on both benchmark image databases and synthetic data. Various comparisons with other state-of-the-art learning techniques are investigated.

AB - In image classification and other learning-based object recognition tasks, it is often tedious and expensive to label large training data sets. Discriminant-EM (DEM) proposed a semi-supervised learning framework which takes both labeled and unlabeled data to learn classifiers. This paper extends the linear D-EM to nonlinear kernel algorithm, KDEM and evaluates KDEM on both benchmark image databases and synthetic data. Various comparisons with other state-of-the-art learning techniques are investigated.

UR - http://www.scopus.com/inward/record.url?scp=4544300314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544300314&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:4544300314

VL - 5

SP - V-461-V-464

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

SN - 0736-7791

ER -