Fusion of dominant colour and spatial layout features for effective image retrieval of coloured logos and trademarks

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

10 Citations (Scopus)

Abstract

Due to its uniqueness and high value in commercial side, logos and trademarks play a key role in e-business based global marketing. Detecting misused and faked logos need designated and accurate image processing and retrieval techniques. However, existing colour and shape based retrieval techniques, which are mainly designed for natural images, cannot provide effective retrieval of logo images. In this paper, an effective approach is proposed for content-based image retrieval of coloured logos and trademarks. By extracting the dominant colour from colour quantization and measuring the spatial similarity, fusion of colour and spatial layout features is achieved. The proposed approach has been tested on a database containing over 250 logo images. Experimental results show that the proposed methodology yields more accurate results in retrieving relevant images than conventional approaches even with added Gaussian and Salt&pepper noise.
LanguageEnglish
Title of host publication2015 IEEE International Conference on Multimedia Big Data
PublisherIEEE
Pages306 - 311
Number of pages6
ISBN (Print)978-1-4799-8688-0
DOIs
Publication statusPublished - Apr 2015

Fingerprint

Trademarks
Image retrieval
Fusion reactions
Color
Marketing
Image processing
Salts
Industry

Keywords

  • image retrieval
  • dominant colour descriptor
  • spatial layout
  • logo and trademark retrieval

Cite this

@inproceedings{a992e60c6f844237b3f0acf86257a422,
title = "Fusion of dominant colour and spatial layout features for effective image retrieval of coloured logos and trademarks",
abstract = "Due to its uniqueness and high value in commercial side, logos and trademarks play a key role in e-business based global marketing. Detecting misused and faked logos need designated and accurate image processing and retrieval techniques. However, existing colour and shape based retrieval techniques, which are mainly designed for natural images, cannot provide effective retrieval of logo images. In this paper, an effective approach is proposed for content-based image retrieval of coloured logos and trademarks. By extracting the dominant colour from colour quantization and measuring the spatial similarity, fusion of colour and spatial layout features is achieved. The proposed approach has been tested on a database containing over 250 logo images. Experimental results show that the proposed methodology yields more accurate results in retrieving relevant images than conventional approaches even with added Gaussian and Salt&pepper noise.",
keywords = "image retrieval, dominant colour descriptor, spatial layout, logo and trademark retrieval",
author = "Yijun Yan and Jinchang Ren and Yinsheng Li and James Windmill and Winifred Ijomah",
note = "(c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.",
year = "2015",
month = "4",
doi = "10.1109/BigMM.2015.43",
language = "English",
isbn = "978-1-4799-8688-0",
pages = "306 -- 311",
booktitle = "2015 IEEE International Conference on Multimedia Big Data",
publisher = "IEEE",

}

Fusion of dominant colour and spatial layout features for effective image retrieval of coloured logos and trademarks. / Yan, Yijun; Ren, Jinchang; Li, Yinsheng; Windmill, James; Ijomah, Winifred.

2015 IEEE International Conference on Multimedia Big Data. IEEE, 2015. p. 306 - 311.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Fusion of dominant colour and spatial layout features for effective image retrieval of coloured logos and trademarks

AU - Yan, Yijun

AU - Ren, Jinchang

AU - Li, Yinsheng

AU - Windmill, James

AU - Ijomah, Winifred

N1 - (c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

PY - 2015/4

Y1 - 2015/4

N2 - Due to its uniqueness and high value in commercial side, logos and trademarks play a key role in e-business based global marketing. Detecting misused and faked logos need designated and accurate image processing and retrieval techniques. However, existing colour and shape based retrieval techniques, which are mainly designed for natural images, cannot provide effective retrieval of logo images. In this paper, an effective approach is proposed for content-based image retrieval of coloured logos and trademarks. By extracting the dominant colour from colour quantization and measuring the spatial similarity, fusion of colour and spatial layout features is achieved. The proposed approach has been tested on a database containing over 250 logo images. Experimental results show that the proposed methodology yields more accurate results in retrieving relevant images than conventional approaches even with added Gaussian and Salt&pepper noise.

AB - Due to its uniqueness and high value in commercial side, logos and trademarks play a key role in e-business based global marketing. Detecting misused and faked logos need designated and accurate image processing and retrieval techniques. However, existing colour and shape based retrieval techniques, which are mainly designed for natural images, cannot provide effective retrieval of logo images. In this paper, an effective approach is proposed for content-based image retrieval of coloured logos and trademarks. By extracting the dominant colour from colour quantization and measuring the spatial similarity, fusion of colour and spatial layout features is achieved. The proposed approach has been tested on a database containing over 250 logo images. Experimental results show that the proposed methodology yields more accurate results in retrieving relevant images than conventional approaches even with added Gaussian and Salt&pepper noise.

KW - image retrieval

KW - dominant colour descriptor

KW - spatial layout

KW - logo and trademark retrieval

UR - http://www.bigmm2015.org/

U2 - 10.1109/BigMM.2015.43

DO - 10.1109/BigMM.2015.43

M3 - Conference contribution book

SN - 978-1-4799-8688-0

SP - 306

EP - 311

BT - 2015 IEEE International Conference on Multimedia Big Data

PB - IEEE

ER -