Color distribution matching using a weighted subspace descriptor

研究成果: Conference contribution

1 引用 (Scopus)

抄録

This paper presents a low-level color descriptor which describes the color distribution of a color image as a weighted subspace in the color space, namely eigenvectors and eigenvalues of the distribution. Thanks to low-dimensionality of color space, the proposed descriptor can provide compact description and fast computation. Furthermore, specialized for color distribution matching, it is more efficient than mutual subspace method (MSM). Experiments on medicine package recognition validate that the proposed descriptor outperforms MSM and MPEG-7 low-level color descriptors in terms of description size, computational cost and recognition rate.

元の言語English
ホスト出版物のタイトルProceedings - International Conference on Image Processing, ICIP
ページ1697-1700
ページ数4
DOI
出版物ステータスPublished - 2011
イベント2011 18th IEEE International Conference on Image Processing, ICIP 2011 - Brussels
継続期間: 2011 9 112011 9 14

Other

Other2011 18th IEEE International Conference on Image Processing, ICIP 2011
Brussels
期間11/9/1111/9/14

Fingerprint

Color
Eigenvalues and eigenfunctions
Medicine
Costs
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

これを引用

Sugimoto, K., & Kamata, S. (2011). Color distribution matching using a weighted subspace descriptor. : Proceedings - International Conference on Image Processing, ICIP (pp. 1697-1700). [6115783] https://doi.org/10.1109/ICIP.2011.6115783

Color distribution matching using a weighted subspace descriptor. / Sugimoto, Kenjiro; Kamata, Seiichiro.

Proceedings - International Conference on Image Processing, ICIP. 2011. p. 1697-1700 6115783.

研究成果: Conference contribution

Sugimoto, K & Kamata, S 2011, Color distribution matching using a weighted subspace descriptor. : Proceedings - International Conference on Image Processing, ICIP., 6115783, pp. 1697-1700, 2011 18th IEEE International Conference on Image Processing, ICIP 2011, Brussels, 11/9/11. https://doi.org/10.1109/ICIP.2011.6115783
Sugimoto K, Kamata S. Color distribution matching using a weighted subspace descriptor. : Proceedings - International Conference on Image Processing, ICIP. 2011. p. 1697-1700. 6115783 https://doi.org/10.1109/ICIP.2011.6115783
Sugimoto, Kenjiro ; Kamata, Seiichiro. / Color distribution matching using a weighted subspace descriptor. Proceedings - International Conference on Image Processing, ICIP. 2011. pp. 1697-1700
@inproceedings{70b75781c47c456ca59a87447fb632f6,
title = "Color distribution matching using a weighted subspace descriptor",
abstract = "This paper presents a low-level color descriptor which describes the color distribution of a color image as a weighted subspace in the color space, namely eigenvectors and eigenvalues of the distribution. Thanks to low-dimensionality of color space, the proposed descriptor can provide compact description and fast computation. Furthermore, specialized for color distribution matching, it is more efficient than mutual subspace method (MSM). Experiments on medicine package recognition validate that the proposed descriptor outperforms MSM and MPEG-7 low-level color descriptors in terms of description size, computational cost and recognition rate.",
keywords = "Low-level color descriptor, medicine package recognition, mutual sub-space method",
author = "Kenjiro Sugimoto and Seiichiro Kamata",
year = "2011",
doi = "10.1109/ICIP.2011.6115783",
language = "English",
isbn = "9781457713033",
pages = "1697--1700",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Color distribution matching using a weighted subspace descriptor

AU - Sugimoto, Kenjiro

AU - Kamata, Seiichiro

PY - 2011

Y1 - 2011

N2 - This paper presents a low-level color descriptor which describes the color distribution of a color image as a weighted subspace in the color space, namely eigenvectors and eigenvalues of the distribution. Thanks to low-dimensionality of color space, the proposed descriptor can provide compact description and fast computation. Furthermore, specialized for color distribution matching, it is more efficient than mutual subspace method (MSM). Experiments on medicine package recognition validate that the proposed descriptor outperforms MSM and MPEG-7 low-level color descriptors in terms of description size, computational cost and recognition rate.

AB - This paper presents a low-level color descriptor which describes the color distribution of a color image as a weighted subspace in the color space, namely eigenvectors and eigenvalues of the distribution. Thanks to low-dimensionality of color space, the proposed descriptor can provide compact description and fast computation. Furthermore, specialized for color distribution matching, it is more efficient than mutual subspace method (MSM). Experiments on medicine package recognition validate that the proposed descriptor outperforms MSM and MPEG-7 low-level color descriptors in terms of description size, computational cost and recognition rate.

KW - Low-level color descriptor

KW - medicine package recognition

KW - mutual sub-space method

UR - http://www.scopus.com/inward/record.url?scp=84856272104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856272104&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2011.6115783

DO - 10.1109/ICIP.2011.6115783

M3 - Conference contribution

AN - SCOPUS:84856272104

SN - 9781457713033

SP - 1697

EP - 1700

BT - Proceedings - International Conference on Image Processing, ICIP

ER -