Generic Object Recognition Using Graph Embedding into A Vector Space

Takahiro Hori; Tetsuya Takiguchi; Yasuo Ariki

doi:doi:10.11648/j.ajsea.20130201.13

| Peer-Reviewed

Generic Object Recognition Using Graph Embedding into A Vector Space

Takahiro Hori, Tetsuya Takiguchi, Yasuo Ariki

Published in American Journal of Software Engineering and Applications (Volume 2, Issue 1)

Published: 20 February 2013

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by computer is finding extensive use in a variety of fields, including robotic vision and image retrieval. Conventional methods use a bag-of-features (BoF) approach, which expresses the image as an appearance fre-quency histogram of visual words by quantizing SIFT (Scale-Invariant Feature Transform) features. However, there is a problem associated with this approach, namely that the location information and the relationship between keypoints (both of which are important as structural information) are lost. To deal with this problem, in the proposed method, the graph is constructed by connecting SIFT keypoints with lines. As a result, the keypoints maintain their relationship, and then structural representation with location information is achieved. Since graph representation is not suitable for statistical work, the graph is embedded into a vector space according to the graph edit distance. The experiment results on two image datasets of multi-class showed that the proposed method improved the recognition rate.

Published in	American Journal of Software Engineering and Applications (Volume 2, Issue 1)
DOI	10.11648/j.ajsea.20130201.13
Page(s)	13-18
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2013. Published by Science Publishing Group

Keywords

Generic object recognition; Graph edit distance; SIFT

References

[1]	K. Barnard and D. A. Forsyth, "Learning the semantics of words and pictures," Proc. of IEEE International Conf. on Computer Vision, pp. 408–415, 2001.
[2]	K. Barnard, P. Duygulu, N. de Freitas, and D. Forsyth, "Matching words and pictures," Journal of Machine Learning Research, vol. 3, pp. 1107–1135, 2003.
[3]	P. Duygulu,K. Barnard, N. de Freitas, and D. Forsyth, "Vis-ual categorization with bags of keypoints," Proc. of European Conference on Computer Vision, pp. 97–112, 2002.
[4]	G. Csurka, C.R. Dance, L. Fan, J. Willamowski, and C.Bray, "Object Recognition as Machine Translation:Learning Lex-icons for a Fixed Image Vocabulary," Proc. of ECCV work-shop on Statistical Learning in Computer Vision, pp. 1–22, 2004.
[5]	D. G. Low, "Distinctive image features from scale invariant keypoints," Journal of Computer Vision, vol. 60, pp. 91–110, 2004.
[6]	J. Revaud, Y. Ariki, and A. Baskurt, "Scale-Invariant Prox-imity Graph for Fast Probabilistic Object Recognition," Proc. of Conference on Image and Video Retrieval, pp. 414–421, 2010.
[7]	D. Conte, P. Foggia, C. Sansone, and M. Vento, "Thirty years of graph matching in pattern recognition," International Journal of Pattern Recognition and Artificial Intelligence, vol. 8, pp. 265–298, 2004.
[8]	H. Bunke and G. Allerman, "Inexact graph matching for structural pattern recognition,"Pattern Recognition Letters, vol. 1, pp. 245–253, 1983.
[9]	A. Sanfeliu and K. Fu, "A distance measure between attri-buted relational graphs for pattern recognition,"IEEE Transactions on Systems, Man, and Cybernetics, vol. 13, pp. 353–362, 1983.
[10]	D. Justice and A. Hero, "A Binary Linear Programming Formulation of the Graph Edit Distance,"IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, pp. 1200–1214, 2006.
[11]	M. Neuhaus, K. Riesen, and H. Bunke, "Fast suboptimal algorithms for the computation of graph edit distance,"Joint IAPR International Workshops, SSPR and SPR 2006, Lec-ture Notes in Computer Science, vol. 4109, pp. 163–172, 2006.
[12]	K. Riesen and H. Bunke, "Approximate graph edit distance computation by means of bipartite graph matching,"Image and Vision Computing, vol. 27, pp. 950–959, 2009.
[13]	K. Riesen, M. Neuhaus, and H. Bunke, "Graph Embedding in Vector Spaces by Means of Prototype Selec-tion,"Graph-based representations in pattern recognition (GbRPR), F. Escolano et al, Ed., Springer-Verlag Berlin, Heidelberg, pp. 383–393, 2007.
[14]	E. Valveny and M. Ferrer, "Application of Graph Embedding to solve Graph Matching Problems,"Proc. of CIFED, pp. 13–18, 2008.
[15]	M. Ferrer, E. Valveny, F. Serratosa, K. Riesen, and H.Bunke, "Generalized median graph computation by means of graph embedding in vector spaces,"Pattern Recognition, vol. 43, pp. 1642–1655, 2010.
[16]	C. Cortes and V. Vapnik, "Support-Vector Networks," Ma-chine Learning, vol. 20, pp. 273–297, 1995.

Cite This Article

Plain Text BibTeX RIS

APA Style

Takahiro Hori, Tetsuya Takiguchi, Yasuo Ariki. (2013). Generic Object Recognition Using Graph Embedding into A Vector Space. American Journal of Software Engineering and Applications, 2(1), 13-18. https://doi.org/10.11648/j.ajsea.20130201.13

Copy | Download

ACS Style

Takahiro Hori; Tetsuya Takiguchi; Yasuo Ariki. Generic Object Recognition Using Graph Embedding into A Vector Space. Am. J. Softw. Eng. Appl. 2013, 2(1), 13-18. doi: 10.11648/j.ajsea.20130201.13

Copy | Download

AMA Style

Takahiro Hori, Tetsuya Takiguchi, Yasuo Ariki. Generic Object Recognition Using Graph Embedding into A Vector Space. Am J Softw Eng Appl. 2013;2(1):13-18. doi: 10.11648/j.ajsea.20130201.13

Copy | Download

@article{10.11648/j.ajsea.20130201.13,
  author = {Takahiro Hori and Tetsuya Takiguchi and Yasuo Ariki},
  title = {Generic Object Recognition Using Graph Embedding into A Vector Space},
  journal = {American Journal of Software Engineering and Applications},
  volume = {2},
  number = {1},
  pages = {13-18},
  doi = {10.11648/j.ajsea.20130201.13},
  url = {https://doi.org/10.11648/j.ajsea.20130201.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajsea.20130201.13},
  abstract = {This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by computer is finding extensive use in a variety of fields, including robotic vision and image retrieval. Conventional methods use a bag-of-features (BoF) approach, which expresses the image as an appearance fre-quency histogram of visual words by quantizing SIFT (Scale-Invariant Feature Transform) features. However, there is a problem associated with this approach, namely that the location information and the relationship between keypoints (both of which are important as structural information) are lost. To deal with this problem, in the proposed method, the graph is constructed by connecting SIFT keypoints with lines. As a result, the keypoints maintain their relationship, and then structural representation with location information is achieved. Since graph representation is not suitable for statistical work, the graph is embedded into a vector space according to the graph edit distance. The experiment results on two image datasets of multi-class showed that the proposed method improved the recognition rate.},
 year = {2013}
}

Copy | Download

TY  - JOUR
T1  - Generic Object Recognition Using Graph Embedding into A Vector Space
AU  - Takahiro Hori
AU  - Tetsuya Takiguchi
AU  - Yasuo Ariki
Y1  - 2013/02/20
PY  - 2013
N1  - https://doi.org/10.11648/j.ajsea.20130201.13
DO  - 10.11648/j.ajsea.20130201.13
T2  - American Journal of Software Engineering and Applications
JF  - American Journal of Software Engineering and Applications
JO  - American Journal of Software Engineering and Applications
SP  - 13
EP  - 18
PB  - Science Publishing Group
SN  - 2327-249X
UR  - https://doi.org/10.11648/j.ajsea.20130201.13
AB  - This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by computer is finding extensive use in a variety of fields, including robotic vision and image retrieval. Conventional methods use a bag-of-features (BoF) approach, which expresses the image as an appearance fre-quency histogram of visual words by quantizing SIFT (Scale-Invariant Feature Transform) features. However, there is a problem associated with this approach, namely that the location information and the relationship between keypoints (both of which are important as structural information) are lost. To deal with this problem, in the proposed method, the graph is constructed by connecting SIFT keypoints with lines. As a result, the keypoints maintain their relationship, and then structural representation with location information is achieved. Since graph representation is not suitable for statistical work, the graph is embedded into a vector space according to the graph edit distance. The experiment results on two image datasets of multi-class showed that the proposed method improved the recognition rate.
VL  - 2
IS  - 1
ER  -

Copy | Download

Author Information

Takahiro Hori

Graduate School of System Informatics, Kobe University, Japan
Tetsuya Takiguchi

Graduate School of System Informatics, Kobe University, Japan
Yasuo Ariki

Graduate School of System Informatics, Kobe University, Japan

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Takahiro Hori, Tetsuya Takiguchi, Yasuo Ariki. (2013). Generic Object Recognition Using Graph Embedding into A Vector Space. American Journal of Software Engineering and Applications, 2(1), 13-18. https://doi.org/10.11648/j.ajsea.20130201.13

Copy | Download

ACS Style

Takahiro Hori; Tetsuya Takiguchi; Yasuo Ariki. Generic Object Recognition Using Graph Embedding into A Vector Space. Am. J. Softw. Eng. Appl. 2013, 2(1), 13-18. doi: 10.11648/j.ajsea.20130201.13

Copy | Download

AMA Style

Takahiro Hori, Tetsuya Takiguchi, Yasuo Ariki. Generic Object Recognition Using Graph Embedding into A Vector Space. Am J Softw Eng Appl. 2013;2(1):13-18. doi: 10.11648/j.ajsea.20130201.13

Copy | Download

@article{10.11648/j.ajsea.20130201.13,
  author = {Takahiro Hori and Tetsuya Takiguchi and Yasuo Ariki},
  title = {Generic Object Recognition Using Graph Embedding into A Vector Space},
  journal = {American Journal of Software Engineering and Applications},
  volume = {2},
  number = {1},
  pages = {13-18},
  doi = {10.11648/j.ajsea.20130201.13},
  url = {https://doi.org/10.11648/j.ajsea.20130201.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajsea.20130201.13},
  abstract = {This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by computer is finding extensive use in a variety of fields, including robotic vision and image retrieval. Conventional methods use a bag-of-features (BoF) approach, which expresses the image as an appearance fre-quency histogram of visual words by quantizing SIFT (Scale-Invariant Feature Transform) features. However, there is a problem associated with this approach, namely that the location information and the relationship between keypoints (both of which are important as structural information) are lost. To deal with this problem, in the proposed method, the graph is constructed by connecting SIFT keypoints with lines. As a result, the keypoints maintain their relationship, and then structural representation with location information is achieved. Since graph representation is not suitable for statistical work, the graph is embedded into a vector space according to the graph edit distance. The experiment results on two image datasets of multi-class showed that the proposed method improved the recognition rate.},
 year = {2013}
}

Copy | Download

TY  - JOUR
T1  - Generic Object Recognition Using Graph Embedding into A Vector Space
AU  - Takahiro Hori
AU  - Tetsuya Takiguchi
AU  - Yasuo Ariki
Y1  - 2013/02/20
PY  - 2013
N1  - https://doi.org/10.11648/j.ajsea.20130201.13
DO  - 10.11648/j.ajsea.20130201.13
T2  - American Journal of Software Engineering and Applications
JF  - American Journal of Software Engineering and Applications
JO  - American Journal of Software Engineering and Applications
SP  - 13
EP  - 18
PB  - Science Publishing Group
SN  - 2327-249X
UR  - https://doi.org/10.11648/j.ajsea.20130201.13
AB  - This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by computer is finding extensive use in a variety of fields, including robotic vision and image retrieval. Conventional methods use a bag-of-features (BoF) approach, which expresses the image as an appearance fre-quency histogram of visual words by quantizing SIFT (Scale-Invariant Feature Transform) features. However, there is a problem associated with this approach, namely that the location information and the relationship between keypoints (both of which are important as structural information) are lost. To deal with this problem, in the proposed method, the graph is constructed by connecting SIFT keypoints with lines. As a result, the keypoints maintain their relationship, and then structural representation with location information is achieved. Since graph representation is not suitable for statistical work, the graph is embedded into a vector space according to the graph edit distance. The experiment results on two image datasets of multi-class showed that the proposed method improved the recognition rate.
VL  - 2
IS  - 1
ER  -

Copy | Download