Abstract In order to improve the accuracy and efficiency of extracting features for 3D models retrieval, a novel approach using 3D radon transform and Bag-of-Visual-Features is proposed in this paper. Firstly the 3D radon transform is employed to obtain a view image using the different features in different angels. Then a set of local descriptor vectors are extracted by the SURF algorithm from the local features of the view. The similarity distance between geometrical transformed models is evaluated by using K-means algorithm to verify the geometric invariance of the proposed method. The numerical experiments are conducted to evaluate the retrieval efficiency compared to other typical methods. The experimental results show that the change of parameters has small effect on the retrieval performance of the proposed method.

References

[1] Akgul C., Axenopoulos C., Bustos B., Chaouch M., Daras P., Dutagaci H., Godil1 A., Furuya T., Godil A., Kreft S., Lian Z., and Napoleon T., “SHREC 2009-Generic Shape Retrieval Contest,” in Proceedings of Eurographics Workshop on 3D Object Retrieval, Munich, pp. 61-68, 2009.

[2] Chen F., Ji R., and Cao L., “Multimodal Learning for View-Based 3D Object Classification,” Neurocomputing, vol. 195, pp. 23-29, 2016.

[3] D’Acunto M., Benassi A., Moroni D., and Salvetti O., “3D Image Reconstruction Using 5DGRQ 7UDQVIRUP´Signal, Image and Video Processing Journal, vol. 10, no. 1, pp. 1-8, 2016.

[4] Daras P., Zarpalas D., Tzovaras D., and Strintzis M., “Efficient 3-D Model Search and Retrieval Using Generalized 3-D Radon Transforms,” IEEE Transactions on Multimedia, vol. 8, no. 1, pp. 101-114, 2006.

[5] Daras P., Zarpalas D., Tzovaras D., and Strintzis M., “Shape Matching Using The 3D Radon 7UDQVIRUP´in Proceedings of the 2nd International Symposium on 3D Data Processing, Visualization, and Transmission, Thessaloniki, pp. 953-960, 2004.

[6] Desbat L. and Perrier V., “on Locality of Radon to Riesz Transform,” Signal Processing, vol. 120, pp. 13-25, 2016.

[7] Fang R., Godil A., Li X., and Wagan A., “A New Shape Benchmark for 3D Object Retrieval,” in Proceedings of the 4th International Symposium on Advances in Visual Computing, Las Vegas, pp. 381–392, 2008.

[8] Furuya T. and Ohbuchi R., “Dense Sampling and Fast Encoding for 3D Model Retrieval Using Bag-of-Visual Features,” in Proceedings of the ACM International Conference on Image and Video Retrieval, New York, pp. 1-8, 2009.

[9] Gao Y. and Dai Q., “Efficient View-Based 3-D Object Retrieval via Hypergraph Learning,” Tsinghua Science and Technology, vol. 19, no. 3, pp. 250-256, 2014.

[10] Gao Y., Wang M., Tao D., Ji R., and Dai Q., “3-D Object Retrieval and Recognition with Hypergraph Analysis,” IEEE Transactions on Image Processing, vol. 21, no. 9, pp. 4290-4303, 2012.

[11] Lian Z., Godil A., and Sun X., “Visual Similarity Based 3D Shape Retrieval Using Bag-of- Features,” in Proceedings of Shape Modeling International Conference, Washington, pp. 25-36, 2010.

[12] Liu Y., Wang X., Wang H., Zha H., and Qin H., “Learning Robust Similarity Measures for 3D 3DUWLDO 6KDSH 5HWULHYDO´International Journal of Computer Vision, vol. 89, no. 2, pp. 408-431, 2010.

[13] Lowe D., “Distinctive Image Features from Scale-Invariant Keypoint,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.

[14] Ma J., Kang B., Ma Z., and Lu K., “A Method of Protein Model Classification and Retrieval Using Bag-of-Visual-Features,” Computational and Mathematical Methods in Medicine, 2014

[15] Mahmoud W. and Shaker M., “3D Ear Print $XWKHQWLFDWLRQ 8VLQJ ' 5DGRQ 7UDQVIRUP´ Information and Communication Technologies, pp. 1052-1056, 2006.

[16] Miaoa Q., Liua J., and Lib W., “Three Novel Invariant Moments Based on Radon and Polar Harmonic Transforms,” Optics Communications, vol. 285, no. 6, pp. 1044-1048, 2012.

[17] Ohbuchi R., “Squeezing Bag-of-Features for Scalable and Semantic 3D Models Retrieval,” in Proceedings of the 8th International Workshope on Content-Based Multimedia Indexing, 2010.

[18] Passalis G., Theoharis T., and Kakadiaris I., “PTK: A Novel Depth Buffer-Based Shape Descriptor for Three-Dimensional Object Retrieval,” The Visual Computer, vol. 23, no. 1, pp. 5-14, 2007.

[19] Sfikas K., Theoharis T., and Pratikakis I., “3D Object Retrieval via Range Image Queries in a Bag-of-Visual-Words Context,” The Visual Computer, vol. 29, no. 12, pp. 1351-1361, 2013.

[20] Shih J., Lee C., and Wang J., “A New 3D Model Retrieval Approach Based on the Evevation Descriptor,” Pattern Recognition, vol. 40, no. 1, pp. 283-295, 2007.

[21] Shilane P, Min P., and Kazhdan M., “The Princeton Shape Beachmark,” in Proceedings of the Shape Modeling International, pp. 167-178, 2004.

[22] Siddiqi K., Zhang J., and Macrini D., “Retrieving articulated 3-d models using medial surfaces,” Machine Vision and Applications, vol. 19, pp. 261-275, 2008.

[23] Silkan H., Ouatik S., and Lachkar A., “Extreme Curvature Scale Space for Efficient Shape Similarity Retrieval,” The International Arab Journal of Information Technology, vol. 13, no. 6A, pp. 203-207, 2016

[24] Toldo R., Castellani U., and Fusiello A., “A Bag of Words Approach for 3D Object Categorization,” in Proceedings of the 4th International Conference on Computer, Vision/ Computer Graphics Collaboration Techniques, pp. 116-127, 2009.

[25] Wang F., Peng J., and Li Y., “Hypergraph Based Feature Fusion for 3-D Object Retrieval,” Neurocomputing, no. 151, pp. 12-619, 2015.

[26] Wong A. K. C., Lu S. W., and Rioux M., “Recognition and Shape Synthesis of 3-D Objects Based on Attributed Hypergraphs,” 3D Radon Transform for Shape Retrieval Using Bag-of-Visual-Features 479 IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 3, pp. 279-290, 1989.

[27] Xia S., and Hancock E. R., “Learning Large Scale Class Specific Hyper Graphs for Object Recognition,” in Proceedings of the 5th International Conference on Image and Graphics, Perth Australia pp. 366-371, 2009.

[28] Xiao J., Fengn Y., and Ji M., “Fast View-Based 3D Model Retrieval Via Unsupervised Multiple Feature Fusion and Online Projection Learning,” Signal Processing, no. 120, pp. 702-713, 2016.

[29] Yuvaraj J., and Hariharan S., “Content-Based Image Retrieval Based on Integrating Region Segmentation and Colour Histogram,” The International Arab Journal of Information Technology, Vol. 13, No. 1A, pp. 203-207, 2016

[30] Zarpalas D., Daras P., and Tzovaras D., “3D Model Search and Retrieval Based on the 3D Radon Transform,” in Proceedings of IEEE International Conference on Communications, pp. 1375-1379, 2004.

[31] Zhao S., Yao H., and Zhang Y., “View-based 3D object retrieval via multi-modal graph learning,” Signal Processing, no. 112, pp. 110-118, 2015. Jinlin Ma He received the B.S. degree in Computer Institute from North University for Nationalities, Yinchuan, China in 1999 and received the M.S. degree in Institute of Mathematics & Computer from Ningxia University, Yinchuan, China in 2009. He received his Ph.D. degree at Northwest University, Xi’an, China in 2015. His research interests is in image processing and 3D models retrieval. Ziping Ma She received the B.S. degree in Computer Institute from North University for Nationalities, Yinchuan, China in 2003 and received the M.S. degree in Institute of Mathematics & Computer from Ningxia University, Yinchuan, China in 2006. She received her Ph.D. degree at Northwest University, Xi’an, China in 2013. Her research interests is in image processing and 3D models retrieval.