Sketch-Based Image Retrieval Using Angular Partitioning

A. Chalechale; G. Naghdy; Alfred Mertins

doi:10.1109/ISSPIT.2003.1341209

Sketch-Based Image Retrieval Using Angular Partitioning

A. Chalechale, G. Naghdy, Alfred Mertins

Institute of Signal Processing

University of Wollongong

Abstract

This paper presents a novel approach for sketch-based image retrieval based on low-level features. The approach enables measuring the similarity between a full color image and a simple black and white sketched query and needs no cost intensive image segmentation. The proposed method can cope with images containing several complex objects in an inhomogeneous background. Abstract images are obtained using strong edges of the model image and thinned outline of the sketched image. Angular-spatial distribution of pixels in the abstract images is then employed to extract new compact and effective features using Fourier transform. The extracted features are scale and rotation invariant and robust against translation. A collection of paintings and sketches (ART BANK) is used for testing the proposed method. The results are compared with three other well-known approaches within the literature. Experimental results show significant improvement in the recall ratio using the new features.

Original language	English
Title of host publication	Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795)
Number of pages	4
Publisher	IEEE
Publication date	01.01.2003
Pages	668-671
Article number	1341209
ISBN (Print)	0-7803-8292-7
DOIs	https://doi.org/10.1109/ISSPIT.2003.1341209
Publication status	Published - 01.01.2003
Event	3rd IEEE International Symposium on Signal Processing and Information Technology - Maritim Rhein/Main Hotel, Darmstadt, Germany Duration: 14.12.2003 → 17.12.2003 Conference number: 114394

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISSPIT.2003.1341209

Cite this

@inproceedings{1aef65cb8f99451a9798c096d609922d,

title = "Sketch-Based Image Retrieval Using Angular Partitioning",

abstract = "This paper presents a novel approach for sketch-based image retrieval based on low-level features. The approach enables measuring the similarity between a full color image and a simple black and white sketched query and needs no cost intensive image segmentation. The proposed method can cope with images containing several complex objects in an inhomogeneous background. Abstract images are obtained using strong edges of the model image and thinned outline of the sketched image. Angular-spatial distribution of pixels in the abstract images is then employed to extract new compact and effective features using Fourier transform. The extracted features are scale and rotation invariant and robust against translation. A collection of paintings and sketches (ART BANK) is used for testing the proposed method. The results are compared with three other well-known approaches within the literature. Experimental results show significant improvement in the recall ratio using the new features.",

author = "A. Chalechale and G. Naghdy and Alfred Mertins",

year = "2003",

month = jan,

day = "1",

doi = "10.1109/ISSPIT.2003.1341209",

language = "English",

isbn = "0-7803-8292-7",

series = "IEEE Proceedings",

publisher = "IEEE",

pages = "668--671",

booktitle = "Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795)",

note = "3rd IEEE International Symposium on Signal Processing and Information Technology <br/>, ISSPIT 2003 ; Conference date: 14-12-2003 Through 17-12-2003",

}

Chalechale, A, Naghdy, G & Mertins, A 2003, Sketch-Based Image Retrieval Using Angular Partitioning. in Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795)., 1341209, IEEE Proceedings, IEEE, pp. 668-671, 3rd IEEE International Symposium on Signal Processing and Information Technology
, Darmstadt, Hesse, Germany, 14.12.03. https://doi.org/10.1109/ISSPIT.2003.1341209

Sketch-Based Image Retrieval Using Angular Partitioning. / Chalechale, A.; Naghdy, G.; Mertins, Alfred.
Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795). IEEE, 2003. p. 668-671 1341209 (IEEE Proceedings).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Sketch-Based Image Retrieval Using Angular Partitioning

AU - Chalechale, A.

AU - Naghdy, G.

AU - Mertins, Alfred

N1 - Conference code: 114394

PY - 2003/1/1

Y1 - 2003/1/1

N2 - This paper presents a novel approach for sketch-based image retrieval based on low-level features. The approach enables measuring the similarity between a full color image and a simple black and white sketched query and needs no cost intensive image segmentation. The proposed method can cope with images containing several complex objects in an inhomogeneous background. Abstract images are obtained using strong edges of the model image and thinned outline of the sketched image. Angular-spatial distribution of pixels in the abstract images is then employed to extract new compact and effective features using Fourier transform. The extracted features are scale and rotation invariant and robust against translation. A collection of paintings and sketches (ART BANK) is used for testing the proposed method. The results are compared with three other well-known approaches within the literature. Experimental results show significant improvement in the recall ratio using the new features.

AB - This paper presents a novel approach for sketch-based image retrieval based on low-level features. The approach enables measuring the similarity between a full color image and a simple black and white sketched query and needs no cost intensive image segmentation. The proposed method can cope with images containing several complex objects in an inhomogeneous background. Abstract images are obtained using strong edges of the model image and thinned outline of the sketched image. Angular-spatial distribution of pixels in the abstract images is then employed to extract new compact and effective features using Fourier transform. The extracted features are scale and rotation invariant and robust against translation. A collection of paintings and sketches (ART BANK) is used for testing the proposed method. The results are compared with three other well-known approaches within the literature. Experimental results show significant improvement in the recall ratio using the new features.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-70549096418&origin=inward&txGid=ef81521ef441ee5ebd6b29add92f55b8

U2 - 10.1109/ISSPIT.2003.1341209

DO - 10.1109/ISSPIT.2003.1341209

M3 - Conference contribution

SN - 0-7803-8292-7

T3 - IEEE Proceedings

SP - 668

EP - 671

BT - Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795)

PB - IEEE

T2 - 3rd IEEE International Symposium on Signal Processing and Information Technology <br/>

Y2 - 14 December 2003 through 17 December 2003

ER -

Sketch-Based Image Retrieval Using Angular Partitioning

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this