Semi-supervised spectral mapping for enhancing separation between classes

Weiwei Du, Kiichi Urahama

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a spectral mapping technique for semisupervised pattern classification. Importance scores of features are firstly evaluated with a semi-supervised feature selection algorithm by Zhao et al. Training data are then embedded into a low-dimensional space with a spectral mapping derived from the selected and weighted feature vectors with which test data are classified by the nearest neighbor rule. The performance of the proposed pattern classification algorithm is examined with synthetic and real datasets.

Original languageEnglish
Title of host publicationProceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009
Pages187-190
Number of pages4
Publication statusPublished - 2009
Event11th IAPR Conference on Machine Vision Applications, MVA 2009 - Yokohama, Japan
Duration: May 20 2009May 22 2009

Other

Other11th IAPR Conference on Machine Vision Applications, MVA 2009
CountryJapan
CityYokohama
Period5/20/095/22/09

Fingerprint

Pattern recognition
Feature extraction

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Du, W., & Urahama, K. (2009). Semi-supervised spectral mapping for enhancing separation between classes. In Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009 (pp. 187-190)

Semi-supervised spectral mapping for enhancing separation between classes. / Du, Weiwei; Urahama, Kiichi.

Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. p. 187-190.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Du, W & Urahama, K 2009, Semi-supervised spectral mapping for enhancing separation between classes. in Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. pp. 187-190, 11th IAPR Conference on Machine Vision Applications, MVA 2009, Yokohama, Japan, 5/20/09.
Du W, Urahama K. Semi-supervised spectral mapping for enhancing separation between classes. In Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. p. 187-190
Du, Weiwei ; Urahama, Kiichi. / Semi-supervised spectral mapping for enhancing separation between classes. Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. pp. 187-190
@inproceedings{25a1e6063bae4c3f8e8510e5ffa8f034,
title = "Semi-supervised spectral mapping for enhancing separation between classes",
abstract = "We present a spectral mapping technique for semisupervised pattern classification. Importance scores of features are firstly evaluated with a semi-supervised feature selection algorithm by Zhao et al. Training data are then embedded into a low-dimensional space with a spectral mapping derived from the selected and weighted feature vectors with which test data are classified by the nearest neighbor rule. The performance of the proposed pattern classification algorithm is examined with synthetic and real datasets.",
author = "Weiwei Du and Kiichi Urahama",
year = "2009",
language = "English",
isbn = "9784901122092",
pages = "187--190",
booktitle = "Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009",

}

TY - GEN

T1 - Semi-supervised spectral mapping for enhancing separation between classes

AU - Du, Weiwei

AU - Urahama, Kiichi

PY - 2009

Y1 - 2009

N2 - We present a spectral mapping technique for semisupervised pattern classification. Importance scores of features are firstly evaluated with a semi-supervised feature selection algorithm by Zhao et al. Training data are then embedded into a low-dimensional space with a spectral mapping derived from the selected and weighted feature vectors with which test data are classified by the nearest neighbor rule. The performance of the proposed pattern classification algorithm is examined with synthetic and real datasets.

AB - We present a spectral mapping technique for semisupervised pattern classification. Importance scores of features are firstly evaluated with a semi-supervised feature selection algorithm by Zhao et al. Training data are then embedded into a low-dimensional space with a spectral mapping derived from the selected and weighted feature vectors with which test data are classified by the nearest neighbor rule. The performance of the proposed pattern classification algorithm is examined with synthetic and real datasets.

UR - http://www.scopus.com/inward/record.url?scp=84872720634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872720634&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9784901122092

SP - 187

EP - 190

BT - Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009

ER -