Modeling Bottom-Up Visual Attention for Color Images

Congyan LANG; De XU; Ning LI

doi:10.1093/ietisy/e91-d.3.869

Modeling Bottom-Up Visual Attention for Color Images

Congyan LANG, De XU, Ning LI

Full Text Views

0

Share
Cite this

Summary :

Modeling visual attention provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to the modeling bottom-up visual attention. The main contributions are twofold: 1) We use a principal component analysis (PCA) to transform the RGB color space into three principal components, which intrinsically leads to an opponent representation of colors to ensure good saliency analysis. 2) A practicable framework for modeling visual attention is presented based on a region-level reliability analysis for each feature map. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.

Publication: IEICE TRANSACTIONS on Information Vol.E91-D No.3 pp.869-872

Publication Date: 2008/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e91-d.3.869

Type of Manuscript: LETTER

Category: Image Processing and Video Processing

Cite this

Copy

Congyan LANG, De XU, Ning LI, "Modeling Bottom-Up Visual Attention for Color Images" in IEICE TRANSACTIONS on Information, vol. E91-D, no. 3, pp. 869-872, March 2008, doi: 10.1093/ietisy/e91-d.3.869.
Abstract: Modeling visual attention provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to the modeling bottom-up visual attention. The main contributions are twofold: 1) We use a principal component analysis (PCA) to transform the RGB color space into three principal components, which intrinsically leads to an opponent representation of colors to ensure good saliency analysis. 2) A practicable framework for modeling visual attention is presented based on a region-level reliability analysis for each feature map. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.3.869/_p

Copy

@ARTICLE{e91-d_3_869,
author={Congyan LANG, De XU, Ning LI, },
journal={IEICE TRANSACTIONS on Information},
title={Modeling Bottom-Up Visual Attention for Color Images},
year={2008},
volume={E91-D},
number={3},
pages={869-872},
abstract={Modeling visual attention provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to the modeling bottom-up visual attention. The main contributions are twofold: 1) We use a principal component analysis (PCA) to transform the RGB color space into three principal components, which intrinsically leads to an opponent representation of colors to ensure good saliency analysis. 2) A practicable framework for modeling visual attention is presented based on a region-level reliability analysis for each feature map. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.},
keywords={},
doi={10.1093/ietisy/e91-d.3.869},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Modeling Bottom-Up Visual Attention for Color Images
T2 - IEICE TRANSACTIONS on Information
SP - 869
EP - 872
AU - Congyan LANG
AU - De XU
AU - Ning LI
PY - 2008
DO - 10.1093/ietisy/e91-d.3.869
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2008
AB - Modeling visual attention provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to the modeling bottom-up visual attention. The main contributions are twofold: 1) We use a principal component analysis (PCA) to transform the RGB color space into three principal components, which intrinsically leads to an opponent representation of colors to ensure good saliency analysis. 2) A practicable framework for modeling visual attention is presented based on a region-level reliability analysis for each feature map. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.
ER -