A Shape Retrieval Study Based on Geometric Signature

Article Preview

Abstract:

This paper discusses a shape retrieval study based on geometric signature. We apply a variation signature method to extract the geometric feature of shapes. Then, we compare the performance of geometric signature and Fourier descriptor. The geometric signature gets a recall of 74.498%, precision of 71.519%, and F-measure of 72.978% while the Fourier descriptor gets a recall of 18.326%, precision of 17.593%, and F-measure of 17.952%. The proposed method performs better.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

597-601

Citation:

Online since:

November 2011

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Oussalah,Content Based Image Retrieval: Review of State of Art and Future Directions.Image Processing Theory, Tools and Applications.11.(2008),1-10

DOI: 10.1109/ipta.2008.4743799

Google Scholar

[2] Zhanf Dengsheng , Lu Guojun. Review of shape representation and description techniques. Pattern Recognition. 37,(2004),1-19

Google Scholar

[3] Egozi.A, Keller.Y, Guterman.H,Improving Shape Retrieval by Spectral Matching and Meta Similarity.Image Processing, IEEE Transactions on.5(2009),1319 - 1327

DOI: 10.1109/tip.2010.2040448

Google Scholar

[4] ZhangYujin.Content Based Visual information Retrieval.BeiJing.SciencePublishing Inc.(2003)

Google Scholar

[5] Gonzales.Digital Image Processing.BeiJing.Electronics industry Publishing Inc.(2005)

Google Scholar

[6] GEORGE LEIFMAN, RON MEIR, AYELLET TAL. Semantic-oriented 3d shape retrieval using relevance feedback. Visual Comput. (2005)

DOI: 10.1007/s00371-005-0341-z

Google Scholar

[7] http://www.lems.brown.edu/vision/researchAreas/SIID/ shock-matching/ shapes216.tar.gz

Google Scholar