Similar-image retrieval systems using ICA and PCA bases

Naoto Katsumata; Yasuo Matsuyama

doi:10.1109/IJCNN.2005.1556029

Similar-image retrieval systems using ICA and PCA bases

Naoto Katsumata^*, Yasuo Matsuyama

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

Similar-image retrieval systems are presented and evaluated. The new systems directly use image bases via ICA (Independent Component Analysis) and PCA (Principal Component Analysis). These bases can extract source image's information which is viable to define similarity measures. But, the indeterminacy on amplitude and permutation exists. In this paper, similarity measures which can absorb such indeterminacy are presented. Then, carefully designed opinion tests are carried out to compare the new systems' ability with existing ones. The compatibility of color spaces such as RGB, YIQ, and HSV is also examined. By these massive tests, {ICA, HSV} is judged the best. The resulting system is thus proved to be highly competent at the similar-image retrieval.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Pages	1229-1234
Number of pages	6
Volume	2
DOIs	https://doi.org/10.1109/IJCNN.2005.1556029
Publication status	Published - 2005
Event	International Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC Duration: 2005 Jul 31 → 2005 Aug 4

Other

Other	International Joint Conference on Neural Networks, IJCNN 2005
City	Montreal, QC
Period	05/7/31 → 05/8/4

ASJC Scopus subject areas

Software

Access to Document

10.1109/IJCNN.2005.1556029

Cite this

@inproceedings{ebfb1805359143a4b5501e8da9411cff,

title = "Similar-image retrieval systems using ICA and PCA bases",

abstract = "Similar-image retrieval systems are presented and evaluated. The new systems directly use image bases via ICA (Independent Component Analysis) and PCA (Principal Component Analysis). These bases can extract source image's information which is viable to define similarity measures. But, the indeterminacy on amplitude and permutation exists. In this paper, similarity measures which can absorb such indeterminacy are presented. Then, carefully designed opinion tests are carried out to compare the new systems' ability with existing ones. The compatibility of color spaces such as RGB, YIQ, and HSV is also examined. By these massive tests, {ICA, HSV} is judged the best. The resulting system is thus proved to be highly competent at the similar-image retrieval.",

author = "Naoto Katsumata and Yasuo Matsuyama",

year = "2005",

doi = "10.1109/IJCNN.2005.1556029",

language = "English",

isbn = "0780390482",

volume = "2",

pages = "1229--1234",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "International Joint Conference on Neural Networks, IJCNN 2005 ; Conference date: 31-07-2005 Through 04-08-2005",

}

TY - GEN

T1 - Similar-image retrieval systems using ICA and PCA bases

AU - Katsumata, Naoto

AU - Matsuyama, Yasuo

PY - 2005

Y1 - 2005

N2 - Similar-image retrieval systems are presented and evaluated. The new systems directly use image bases via ICA (Independent Component Analysis) and PCA (Principal Component Analysis). These bases can extract source image's information which is viable to define similarity measures. But, the indeterminacy on amplitude and permutation exists. In this paper, similarity measures which can absorb such indeterminacy are presented. Then, carefully designed opinion tests are carried out to compare the new systems' ability with existing ones. The compatibility of color spaces such as RGB, YIQ, and HSV is also examined. By these massive tests, {ICA, HSV} is judged the best. The resulting system is thus proved to be highly competent at the similar-image retrieval.

AB - Similar-image retrieval systems are presented and evaluated. The new systems directly use image bases via ICA (Independent Component Analysis) and PCA (Principal Component Analysis). These bases can extract source image's information which is viable to define similarity measures. But, the indeterminacy on amplitude and permutation exists. In this paper, similarity measures which can absorb such indeterminacy are presented. Then, carefully designed opinion tests are carried out to compare the new systems' ability with existing ones. The compatibility of color spaces such as RGB, YIQ, and HSV is also examined. By these massive tests, {ICA, HSV} is judged the best. The resulting system is thus proved to be highly competent at the similar-image retrieval.

UR - http://www.scopus.com/inward/record.url?scp=33745936366&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745936366&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1556029

DO - 10.1109/IJCNN.2005.1556029

M3 - Conference contribution

AN - SCOPUS:33745936366

SN - 0780390482

SN - 9780780390485

VL - 2

SP - 1229

EP - 1234

BT - Proceedings of the International Joint Conference on Neural Networks

T2 - International Joint Conference on Neural Networks, IJCNN 2005

Y2 - 31 July 2005 through 4 August 2005

ER -

Similar-image retrieval systems using ICA and PCA bases

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this