Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description

Houssem Chatbri; Keisuke Kameyama; Paul H Kwan

doi:10.1109/DICTA.2013.6691528

Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description

Houssem Chatbri, Keisuke Kameyama, Paul H Kwan

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Citations (Scopus)

Abstract

We review available methods for Sketch-Based Image Retrieval (SBIR) and we discuss their limitations. Then, we present two SBIR algorithms: The first algorithm extracts shape features by using support regions calculated for each sketch point, and the second algorithm adapts the Shape Context descriptor [1] to make it scale invariant and enhances its performance in presence of noise. Both algorithms share the property of calculating the feature extraction window according to the sketch size. Experiments and comparative evaluation with state-of-the-art methods show that the proposed algorithms are competitive in distinctiveness capability and robust against noise.

Original language	English
Title of host publication	Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Editors	Paulo de Souza, Ulrich Engelke, Ashfaqur Rahman
Place of Publication	Los Alamitos, United States of America
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	469-476
ISBN (Print)	9781479921263
DOIs	https://doi.org/10.1109/DICTA.2013.6691528
Publication status	Published - 2013
Event	DICTA 2013: International Conference on Digital Image Computing: Techniques and Applications - Hobart, Australia Duration: 26 Nov 2013 → 28 Nov 2013

Conference

Conference	DICTA 2013: International Conference on Digital Image Computing: Techniques and Applications
City	Hobart, Australia
Period	26/11/13 → 28/11/13

Keywords

Image Processing
Pattern Recognition and Data Mining
Computer Vision

Access to Document

10.1109/DICTA.2013.6691528

https://hdl.handle.net/1959.11/13853

Handle.net

Persistent link

Cite this

Chatbri, H., Kameyama, K., & Kwan, P. H. (2013). Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description. In P. de Souza, U. Engelke, & A. Rahman (Eds.), Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA) (pp. 469-476). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/DICTA.2013.6691528

Chatbri, Houssem ; Kameyama, Keisuke ; Kwan, Paul H. / Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description. Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA). editor / Paulo de Souza ; Ulrich Engelke ; Ashfaqur Rahman. Los Alamitos, United States of America : Institute of Electrical and Electronics Engineers (IEEE), 2013. pp. 469-476

@inproceedings{f495080074934d31b80f8a9d83b70d29,

title = "Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description",

abstract = "We review available methods for Sketch-Based Image Retrieval (SBIR) and we discuss their limitations. Then, we present two SBIR algorithms: The first algorithm extracts shape features by using support regions calculated for each sketch point, and the second algorithm adapts the Shape Context descriptor [1] to make it scale invariant and enhances its performance in presence of noise. Both algorithms share the property of calculating the feature extraction window according to the sketch size. Experiments and comparative evaluation with state-of-the-art methods show that the proposed algorithms are competitive in distinctiveness capability and robust against noise.",

keywords = "Image Processing, Pattern Recognition and Data Mining, Computer Vision",

author = "Houssem Chatbri and Keisuke Kameyama and Kwan, \{Paul H\}",

year = "2013",

doi = "10.1109/DICTA.2013.6691528",

language = "English",

isbn = "9781479921263",

pages = "469--476",

editor = "\{de Souza\}, Paulo and Ulrich Engelke and Ashfaqur Rahman",

booktitle = "Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

note = "DICTA 2013: International Conference on Digital Image Computing: Techniques and Applications ; Conference date: 26-11-2013 Through 28-11-2013",

}

Chatbri, H, Kameyama, K & Kwan, PH 2013, Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description. in P de Souza, U Engelke & A Rahman (eds), Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA). Institute of Electrical and Electronics Engineers (IEEE), Los Alamitos, United States of America, pp. 469-476, DICTA 2013: International Conference on Digital Image Computing: Techniques and Applications, Hobart, Australia, 26/11/13. https://doi.org/10.1109/DICTA.2013.6691528

Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description. / Chatbri, Houssem; Kameyama, Keisuke; Kwan, Paul H.
Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA). ed. / Paulo de Souza; Ulrich Engelke; Ashfaqur Rahman. Los Alamitos, United States of America: Institute of Electrical and Electronics Engineers (IEEE), 2013. p. 469-476.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description

AU - Chatbri, Houssem

AU - Kameyama, Keisuke

AU - Kwan, Paul H

PY - 2013

Y1 - 2013

N2 - We review available methods for Sketch-Based Image Retrieval (SBIR) and we discuss their limitations. Then, we present two SBIR algorithms: The first algorithm extracts shape features by using support regions calculated for each sketch point, and the second algorithm adapts the Shape Context descriptor [1] to make it scale invariant and enhances its performance in presence of noise. Both algorithms share the property of calculating the feature extraction window according to the sketch size. Experiments and comparative evaluation with state-of-the-art methods show that the proposed algorithms are competitive in distinctiveness capability and robust against noise.

AB - We review available methods for Sketch-Based Image Retrieval (SBIR) and we discuss their limitations. Then, we present two SBIR algorithms: The first algorithm extracts shape features by using support regions calculated for each sketch point, and the second algorithm adapts the Shape Context descriptor [1] to make it scale invariant and enhances its performance in presence of noise. Both algorithms share the property of calculating the feature extraction window according to the sketch size. Experiments and comparative evaluation with state-of-the-art methods show that the proposed algorithms are competitive in distinctiveness capability and robust against noise.

KW - Image Processing

KW - Pattern Recognition and Data Mining

KW - Computer Vision

UR - https://www.scopus.com/pages/publications/84893299430

U2 - 10.1109/DICTA.2013.6691528

DO - 10.1109/DICTA.2013.6691528

M3 - Conference contribution

SN - 9781479921263

SP - 469

EP - 476

BT - Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

A2 - de Souza, Paulo

A2 - Engelke, Ulrich

A2 - Rahman, Ashfaqur

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Los Alamitos, United States of America

T2 - DICTA 2013: International Conference on Digital Image Computing: Techniques and Applications

Y2 - 26 November 2013 through 28 November 2013

ER -

Chatbri H, Kameyama K, Kwan PH. Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description. In de Souza P, Engelke U, Rahman A, editors, Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA). Los Alamitos, United States of America: Institute of Electrical and Electronics Engineers (IEEE). 2013. p. 469-476 doi: 10.1109/DICTA.2013.6691528

Sketch-Based Image Retrieval By Size-Adaptive and Noise-Robust Feature Description

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this