A 3D Engineering Model Retrieval Algorithm Based on Relevance Feedback and Features Combination

Abstract:

Article Preview

In order to reuse 3D models and design knowledge efficiently, a number of 3D model retrieval algorithms based on content features of models have been proposed in recent years. Although, the features-based methods have achieved some progress, there are two limitations stilly. The first, single content feature cant be suit for all kinds of 3D models; different features have different strengths and weakness. The second, semantic gap, the semantic of model is independent from low-level characteristics. For those two issues, we present a 3D engineering model retrieval algorithm based on relevance feedback and features combination in this paper. The proposed method takes advantage of multiple features by allying them with weights. In the retrieval process, our method utilizes the Particle Swarm Optimization to update the weights dynamically based on users relevance feedback information in order to narrowing the gap between high-level semantic knowledge and low-level content features. The Experiments, based on publicly available 3D model database Engineering Shape Benchmark (ESB) developed by Purdue University, suggested that the proposed approach has better retrieval ability than traditional ones.

Info:

Periodical:

Key Engineering Materials (Volumes 579-580)

Edited by:

Guanglin Wang, Huifeng Wang, Xiang Zhang and Yuefeng Li

Pages:

340-344

Citation:

T. Zhuang et al., "A 3D Engineering Model Retrieval Algorithm Based on Relevance Feedback and Features Combination", Key Engineering Materials, Vols. 579-580, pp. 340-344, 2014

Online since:

September 2013

Export:

Price:

$38.00

[1] N. Iyer, S. Jayainti, K. Lou, Y. Kalyanaraman and K. Ramani: Computer-Aided Design, Vol. 37 (2005) No. 5, pp.509-530.

[2] Y. Baba and K. Nobeoka: Research Policy, Vol. 26 (1998) No. 6, pp.643-659.

[3] F. Takahiko and O. Ryutarou: ACM International Conference on Image and Video Retrieval (Santorini Island, Greece, July 8-12, 2009), pp.192-199.

[4] A. Apostolos, L. Georgios and D. Petros: The 1st ACM International Conference Multimedia Retrieval (Trento, Italy, April 18-20, 2011), pp, 17-20.

[5] Y. Yi, F.P. Nie, D. Xu, J.B. Luo, Y.T. Zhuang and Y.H. Pan: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34 (2012) No. 4, pp.723-742.

[6] J.B. Li, W.H. Sun and L.L. Tang: Neural Computing and Applications, Vol. 22 (2013) No. 3-4, pp.771-781.

[7] R. Osada, T. Funkhouser, B. Chazelle and D. Dobkin: ACM Transactions on Graphics, Vol. 21 (2002) No. 4, pp.807-832.

DOI: https://doi.org/10.1145/571647.571648

[8] J.L. Jun, X.F. Chen and X.T. Zhang: International Conference on Natural Computation (Chongqing, China, May 29-31, 2012), pp.515-518.

[9] X. Hou, X.T. Zhang, T.G. Jin and W.J. Liu: Computer Integrated Manufacturing Systems, Vol. 15 (2009) No. 1, pp.72-81. (In Chinese).

[10] B. Leng: Research on Feature Description and Relevant Feedback Algorithms for 3D Model Retrieval (Ph.D., Tsinghua University, China 2009), pp.38-44. (In Chinese).

[11] S. Havemann, D. Fellner: IEEE Computer Graphics and Applications, Vol. 27 (2007) No. 3, pp.70-76.

[12] G. Leifman, R. Meir and A. Tal: The Visual Computer, Vol. 21 (2005) No. 8-10, pp.865-875.

[13] X.T. Zhang, X.F. Chen, P.Y. Yang, K.Q. Wang and W.M. Zuo: International Conference on Digital Manufacturing and Automation (Changsha, China, December 18-20, 2010) pp.776-779.