Adaptive fusion of color and spatial features for noise-robust retrieval of colored logo and trademark images

Y. Yan, J. Ren, Y. Li, J. F. C. Windmill, W. Ijimah, Kuo-Ming Chao

  • 1 Citations

Abstract

Due to their uniqueness and high value commercially, logos/trademarks play a key role in e-business based global marketing. However, existing trademark/logo retrieval techniques and content-based image retrieval methods are mostly designed for generic images, which cannot provide effective retrieval of trademarks/logos. Although color and spatial features have been intensively investigated for logo image retrieval, in most cases they were applied separately. When these are combined in a fused manner, a fixed weighting is normally used between them which cannot reflect the significance of these features in the images. When the image quality is degraded by various reasons such as noise, the reliability of color and spatial features may change in different ways, such that the weights between them should be adapted to such changes. In this paper, adaptive fusion of color and spatial descriptors is proposed for colored logo/trademark image retrieval. First, color quantization and k-means are combined for effective dominant color extraction. For each extracted dominant color, a component-based spatial descriptor is derived for local features. By analyzing the image histogram, an adaptive fusion of these two features is achieved for more effective logo abstraction and more accurate image retrieval. The proposed approach has been tested on a database containing over 2300 logo/trademark images. Experimental results have shown that the proposed methodology yields improved retrieval precision and outperforms three state-of-the-art techniques even with added Gaussian, salt and pepper, and speckle noise.
Original languageEnglish
JournalMultidimensional Systems and Signal Processing
Volume(In Press)
DOIs
StatePublished - 1 Feb 2016

Fingerprint

Color
Trademarks
Image retrieval
Fusion reactions
Speckle
Image quality
Marketing
Salts
Industry

Keywords

  • Noise-robust image retrieval
  • Dominant color
  • Spatial layout
  • Adaptive fusion
  • Logo and trademark retrieval

Cite this

Adaptive fusion of color and spatial features for noise-robust retrieval of colored logo and trademark images. / Yan, Y.; Ren, J.; Li, Y.; Windmill, J. F. C.; Ijimah, W.; Chao, Kuo-Ming.

In: Multidimensional Systems and Signal Processing, Vol. (In Press), 01.02.2016.

Research output: Contribution to journalArticle

Yan, Y.; Ren, J.; Li, Y.; Windmill, J. F. C.; Ijimah, W.; Chao, Kuo-Ming / Adaptive fusion of color and spatial features for noise-robust retrieval of colored logo and trademark images.

In: Multidimensional Systems and Signal Processing, Vol. (In Press), 01.02.2016.

Research output: Contribution to journalArticle

@article{04b16f9197044bc6939cedcec06ae9b4,
title = "Adaptive fusion of color and spatial features for noise-robust retrieval of colored logo and trademark images",
abstract = "Due to their uniqueness and high value commercially, logos/trademarks play a key role in e-business based global marketing. However, existing trademark/logo retrieval techniques and content-based image retrieval methods are mostly designed for generic images, which cannot provide effective retrieval of trademarks/logos. Although color and spatial features have been intensively investigated for logo image retrieval, in most cases they were applied separately. When these are combined in a fused manner, a fixed weighting is normally used between them which cannot reflect the significance of these features in the images. When the image quality is degraded by various reasons such as noise, the reliability of color and spatial features may change in different ways, such that the weights between them should be adapted to such changes. In this paper, adaptive fusion of color and spatial descriptors is proposed for colored logo/trademark image retrieval. First, color quantization and k-means are combined for effective dominant color extraction. For each extracted dominant color, a component-based spatial descriptor is derived for local features. By analyzing the image histogram, an adaptive fusion of these two features is achieved for more effective logo abstraction and more accurate image retrieval. The proposed approach has been tested on a database containing over 2300 logo/trademark images. Experimental results have shown that the proposed methodology yields improved retrieval precision and outperforms three state-of-the-art techniques even with added Gaussian, salt and pepper, and speckle noise.",
keywords = "Noise-robust image retrieval, Dominant color, Spatial layout, Adaptive fusion, Logo and trademark retrieval",
author = "Y. Yan and J. Ren and Y. Li and Windmill, {J. F. C.} and W. Ijimah and Kuo-Ming Chao",
note = "The full text is currently unavailable on the repository. This article is currently in press. Full citation details will be uploaded when available.",
year = "2016",
month = "2",
doi = "10.1007/s11045-016-0382-7",
volume = "(In Press)",
journal = "Multidimensional Systems and Signal Processing",
issn = "0923-6082",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - Adaptive fusion of color and spatial features for noise-robust retrieval of colored logo and trademark images

AU - Yan,Y.

AU - Ren,J.

AU - Li,Y.

AU - Windmill,J. F. C.

AU - Ijimah,W.

AU - Chao,Kuo-Ming

N1 - The full text is currently unavailable on the repository. This article is currently in press. Full citation details will be uploaded when available.

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Due to their uniqueness and high value commercially, logos/trademarks play a key role in e-business based global marketing. However, existing trademark/logo retrieval techniques and content-based image retrieval methods are mostly designed for generic images, which cannot provide effective retrieval of trademarks/logos. Although color and spatial features have been intensively investigated for logo image retrieval, in most cases they were applied separately. When these are combined in a fused manner, a fixed weighting is normally used between them which cannot reflect the significance of these features in the images. When the image quality is degraded by various reasons such as noise, the reliability of color and spatial features may change in different ways, such that the weights between them should be adapted to such changes. In this paper, adaptive fusion of color and spatial descriptors is proposed for colored logo/trademark image retrieval. First, color quantization and k-means are combined for effective dominant color extraction. For each extracted dominant color, a component-based spatial descriptor is derived for local features. By analyzing the image histogram, an adaptive fusion of these two features is achieved for more effective logo abstraction and more accurate image retrieval. The proposed approach has been tested on a database containing over 2300 logo/trademark images. Experimental results have shown that the proposed methodology yields improved retrieval precision and outperforms three state-of-the-art techniques even with added Gaussian, salt and pepper, and speckle noise.

AB - Due to their uniqueness and high value commercially, logos/trademarks play a key role in e-business based global marketing. However, existing trademark/logo retrieval techniques and content-based image retrieval methods are mostly designed for generic images, which cannot provide effective retrieval of trademarks/logos. Although color and spatial features have been intensively investigated for logo image retrieval, in most cases they were applied separately. When these are combined in a fused manner, a fixed weighting is normally used between them which cannot reflect the significance of these features in the images. When the image quality is degraded by various reasons such as noise, the reliability of color and spatial features may change in different ways, such that the weights between them should be adapted to such changes. In this paper, adaptive fusion of color and spatial descriptors is proposed for colored logo/trademark image retrieval. First, color quantization and k-means are combined for effective dominant color extraction. For each extracted dominant color, a component-based spatial descriptor is derived for local features. By analyzing the image histogram, an adaptive fusion of these two features is achieved for more effective logo abstraction and more accurate image retrieval. The proposed approach has been tested on a database containing over 2300 logo/trademark images. Experimental results have shown that the proposed methodology yields improved retrieval precision and outperforms three state-of-the-art techniques even with added Gaussian, salt and pepper, and speckle noise.

KW - Noise-robust image retrieval

KW - Dominant color

KW - Spatial layout

KW - Adaptive fusion

KW - Logo and trademark retrieval

U2 - 10.1007/s11045-016-0382-7

DO - 10.1007/s11045-016-0382-7

M3 - Article

VL - (In Press)

JO - Multidimensional Systems and Signal Processing

T2 - Multidimensional Systems and Signal Processing

JF - Multidimensional Systems and Signal Processing

SN - 0923-6082

SN - 1573-0824

ER -