Image retrieval using an improved similarity measure: SRIC: Similarity with region importance and consistency

M. K M Rahman; Tommy W.S. Chow

doi:10.1109/ICCITechn.2014.7073066

Image retrieval using an improved similarity measure: SRIC: Similarity with region importance and consistency

M. K M Rahman
, Tommy W.S. Chow

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

Content based image retrieval has become a major research interest recently. This paper presents an improved image similarity measure for image retrieval system. In the region based image comparison, two images are usually compared in terms of sum of the Euclidean distances among their regions. In this work, the image similarity measure is enhanced through a fuzzyfication of regions' importance and inter-region similarity. First, a 'Mutual Consistency' function is defined for regions' comparison to avoid undesired inter-region similarity. Thereafter, an improved 'Region Importance' function is developed to weight the regions of an image for overall image comparison. Utilizing fuzzy concepts of size and shape features of the regions, these two functions impose additional constrains on similarity measure that helps to improve the image retrieval results. Comparative results with the well-known IRM method are given to illustrate the effectiveness of the proposed approach.

Original language	English
Title of host publication	2014 17th International Conference on Computer and Information Technology, ICCIT 2014
Publisher	IEEE
Pages	336-343
ISBN (Print)	9781479962884
DOIs	https://doi.org/10.1109/ICCITechn.2014.7073066
Publication status	Published - 30 Mar 2015
Event	17th International Conference on Computer and Information Technology, ICCIT 2014 - Dhaka, Bangladesh Duration: 22 Dec 2014 → 23 Dec 2014

Conference

Conference	17th International Conference on Computer and Information Technology, ICCIT 2014
Place	Bangladesh
City	Dhaka
Period	22/12/14 → 23/12/14

Research Keywords

Content based image retrieval
Image similarity measure
Region based image comparison
Region importance and mutual consistency

Access Output

10.1109/ICCITechn.2014.7073066

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{4985df079b424de3b03adaaee5d18259,

title = "Image retrieval using an improved similarity measure: SRIC: Similarity with region importance and consistency",

abstract = "Content based image retrieval has become a major research interest recently. This paper presents an improved image similarity measure for image retrieval system. In the region based image comparison, two images are usually compared in terms of sum of the Euclidean distances among their regions. In this work, the image similarity measure is enhanced through a fuzzyfication of regions' importance and inter-region similarity. First, a 'Mutual Consistency' function is defined for regions' comparison to avoid undesired inter-region similarity. Thereafter, an improved 'Region Importance' function is developed to weight the regions of an image for overall image comparison. Utilizing fuzzy concepts of size and shape features of the regions, these two functions impose additional constrains on similarity measure that helps to improve the image retrieval results. Comparative results with the well-known IRM method are given to illustrate the effectiveness of the proposed approach.",

keywords = "Content based image retrieval, Image similarity measure, Region based image comparison, Region importance and mutual consistency",

author = "Rahman, \{M. K M\} and Chow, \{Tommy W.S.\}",

year = "2015",

month = mar,

day = "30",

doi = "10.1109/ICCITechn.2014.7073066",

language = "English",

isbn = "9781479962884",

pages = "336--343",

booktitle = "2014 17th International Conference on Computer and Information Technology, ICCIT 2014",

publisher = "IEEE",

address = "United States",

note = "17th International Conference on Computer and Information Technology, ICCIT 2014 ; Conference date: 22-12-2014 Through 23-12-2014",

}

Rahman, MKM & Chow, TWS 2015, Image retrieval using an improved similarity measure: SRIC: Similarity with region importance and consistency. in 2014 17th International Conference on Computer and Information Technology, ICCIT 2014., 7073066, IEEE, pp. 336-343, 17th International Conference on Computer and Information Technology, ICCIT 2014, Dhaka, Bangladesh, 22/12/14. https://doi.org/10.1109/ICCITechn.2014.7073066

Image retrieval using an improved similarity measure: SRIC: Similarity with region importance and consistency. / Rahman, M. K M; Chow, Tommy W.S.
2014 17th International Conference on Computer and Information Technology, ICCIT 2014. IEEE, 2015. p. 336-343 7073066.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Image retrieval using an improved similarity measure: SRIC

T2 - 17th International Conference on Computer and Information Technology, ICCIT 2014

AU - Rahman, M. K M

AU - Chow, Tommy W.S.

PY - 2015/3/30

Y1 - 2015/3/30

N2 - Content based image retrieval has become a major research interest recently. This paper presents an improved image similarity measure for image retrieval system. In the region based image comparison, two images are usually compared in terms of sum of the Euclidean distances among their regions. In this work, the image similarity measure is enhanced through a fuzzyfication of regions' importance and inter-region similarity. First, a 'Mutual Consistency' function is defined for regions' comparison to avoid undesired inter-region similarity. Thereafter, an improved 'Region Importance' function is developed to weight the regions of an image for overall image comparison. Utilizing fuzzy concepts of size and shape features of the regions, these two functions impose additional constrains on similarity measure that helps to improve the image retrieval results. Comparative results with the well-known IRM method are given to illustrate the effectiveness of the proposed approach.

AB - Content based image retrieval has become a major research interest recently. This paper presents an improved image similarity measure for image retrieval system. In the region based image comparison, two images are usually compared in terms of sum of the Euclidean distances among their regions. In this work, the image similarity measure is enhanced through a fuzzyfication of regions' importance and inter-region similarity. First, a 'Mutual Consistency' function is defined for regions' comparison to avoid undesired inter-region similarity. Thereafter, an improved 'Region Importance' function is developed to weight the regions of an image for overall image comparison. Utilizing fuzzy concepts of size and shape features of the regions, these two functions impose additional constrains on similarity measure that helps to improve the image retrieval results. Comparative results with the well-known IRM method are given to illustrate the effectiveness of the proposed approach.

KW - Content based image retrieval

KW - Image similarity measure

KW - Region based image comparison

KW - Region importance and mutual consistency

U2 - 10.1109/ICCITechn.2014.7073066

DO - 10.1109/ICCITechn.2014.7073066

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781479962884

SP - 336

EP - 343

BT - 2014 17th International Conference on Computer and Information Technology, ICCIT 2014

PB - IEEE

Y2 - 22 December 2014 through 23 December 2014

ER -

Image retrieval using an improved similarity measure: SRIC: Similarity with region importance and consistency

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Fingerprint

Cite this