Scene Retrieval Approach Based Dynamic Bayesian Networks

Abstract:

In this paper, a new materials image retrieval methodology based on dynamic Bayesian network (DBN) is proposed to overcome certain drawbacks inherited in previously proposed CBIR methods. Firstly, the DBN structure and initial parameters is constructed according to the prior knowledge. Secondly, a training phase is conducted for updating DBN parameters through using the feedback information. The training cycles can be stopped until the retrieval accuracy is adequately high. Experimental results on 10,000 images demonstrate the effectiveness of the proposed methodology.

• Periodical: Applied Mechanics and Materials (Volumes 135-136)
• Pages: 873-878
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.135-136.873
• Online since: October 2011
• Authors: Qinkun Xiao, Xiao Xia Hu, Song Gao
• Keywords: DBN Learning, Materials Image Retrieval, Parameter

References

[1] A.L. Dong, B. Bhanu. A new semi-supervised EM algorithm for image retrieval, " CVPR, (2003) vol. 2, pp.662-667.

[2] X.F. He et al. learning a semantic space from user's relevance feedback for image retrieval, IEEE Trans. On CSVT, (2003) vol. 13, no. 1, pp.39-48.

[3] Y. Wu, Q. Tian, T.S. Huang. Discriminant EM algorithm with application to image retrieval, CVPR, (2000) vol. 1, pp.222-227.

[4] R.J. Ong, J.T. Dawley and P.G. Clem: submitted to Journal of Materials Research (2003).

[4] B. Bustos, D.A. Keim, D. Saupe, T. Schreck, and D.V. Vranic. Feature- Based Similarity Search in 3D Object Databases. ACM Computing Surveys, (2005) vol. 37, no. 4, pp.345-387.

DOI: 10.1145/1118890.1118893

[5] D. -Y. Chen, X. -P. Tian, Y. -T. Shen, and M. Ouhyoung, On Visual Similarity Based 3D Model Retrieval, Computer Graphics Forum, (2003 )vol. 22, pp.223-232.

DOI: 10.1111/1467-8659.00669

[6] Akgül Ceyhun Burak, Sankur Bülent, Yemez Yücel, Schmitt Francis. 3D model retrieval using probability density-based shape descriptors. IEEE Trans. on Pattern Analysis and Machine Intelligence, (2009) v 31, n 6, pp.1117-1133.

DOI: 10.1109/tpami.2009.25

[7] Q.K. Xiao, Q.H. Dai and H.Y. Wang. 3D object retrieval approach based on directed acyclic graph lightfield feature. Electronics Letters, (2008) v 44, n 14, p.847–849.

DOI: 10.1049/el:20080314

[8] Kevin Patrick Murphy . Dynamic Bayesian Networks: Representation, Inference and Learning. Ph. D thesis, University of California, Berkeley, (2002).

[9] Bustos Benjamin, Keim Daniel A. ei al. Feature-based similarity search in 3D object databases ACM Computing Surveys, (2005) 37(4): 345–387.

DOI: 10.1145/1118890.1118893

[10] Corel stock photo library, Corel Corp., Ontario, Canada.

[11] R. Osada, T. Funkhouser, B. Chazelle, and D. Dobkin, Shape Distributions, ACM Trans. Graphics, (2002) vol. 21, no. 4, pp.807-832.

DOI: 10.1145/571647.571648

[12] B.K.P. Horn, Extended Gaussian Images, Proc. IEEE, (1984) vol. 72, pp.1671-1686.

DOI: 10.1109/proc.1984.13073

[13] M. Kazhdan, T. Funkhouser, and S. Rusinkiewicz, Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors, Proc. Eurographics/ACM SIGGRAPH Symp. Geometry Processing, (2003) pp.156-164.

DOI: 10.1145/1057432.1057448

[14] Ansary Tarik Filali, Daoudi Mohamed, Vandeborre Jean-Philippe. A bayesian 3-D search engine using adaptive views clustering. IEEE Transactions on Multimedia, (2007) v 9, n 1, pp.78-88.

DOI: 10.1109/tmm.2006.886359

[15] Jau-Ling Shih., Chang-Hsing Lee, Jian TangWang.: A new 3D object retrieval approach based on the elevation descriptor. Pattern Recognition, (2007), v 40, n 1, p.283–295.

DOI: 10.1016/j.patcog.2006.04.034

[16] T. M. Cover and J. A. Thomas. Elements of Information Theory. John Wiley, (1991).