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

Research output: Contribution to journalArticle

11 Citations (Scopus)
86 Downloads (Pure)

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
Pages (from-to)1-24
Number of pages24
JournalMultidimensional Systems and Signal Processing
Early online date1 Feb 2016
DOIs
Publication statusE-pub ahead of print - 1 Feb 2016

Fingerprint

Trademarks
Fusion
Retrieval
Fusion reactions
Image retrieval
Color
Image Retrieval
Descriptors
Color Quantization
Speckle Noise
Content-based Image Retrieval
Local Features
K-means
Electronic Commerce
Salt
Image Quality
Histogram
Weighting
Speckle
Uniqueness

Keywords

  • adaptive fusion
  • dominant color
  • logo and trademark retrieval
  • noise-robust image retrieval
  • spatial layout

Cite this

@article{e392403ceab34cebaa84ce1ffe4c67ca,
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 = "adaptive fusion, dominant color, logo and trademark retrieval, noise-robust image retrieval, spatial layout",
author = "Yijun Yan and Jinchang Ren and Yinsheng Li and Windmill, {James F C} and Winifred Ijomah and Chao, {Kuo Ming}",
year = "2016",
month = "2",
day = "1",
doi = "10.1007/s11045-016-0382-7",
language = "English",
pages = "1--24",
journal = "Multidimensional Systems and Signal Processing",
issn = "0923-6082",

}

TY - JOUR

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

AU - Yan, Yijun

AU - Ren, Jinchang

AU - Li, Yinsheng

AU - Windmill, James F C

AU - Ijomah, Winifred

AU - Chao, Kuo Ming

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 - adaptive fusion

KW - dominant color

KW - logo and trademark retrieval

KW - noise-robust image retrieval

KW - spatial layout

UR - http://www.scopus.com/inward/record.url?scp=84956854134&partnerID=8YFLogxK

U2 - 10.1007/s11045-016-0382-7

DO - 10.1007/s11045-016-0382-7

M3 - Article

SP - 1

EP - 24

JO - Multidimensional Systems and Signal Processing

JF - Multidimensional Systems and Signal Processing

SN - 0923-6082

ER -