Manifold Ranking for Sketch-Based 3D Model Retrieval

详细信息    查看全文

• 关键词：Sketch retrieval ; 3D model ; Manifold ranking ; Visual vocabulary ; Line drawing
• 刊名：Lecture Notes in Computer Science
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：10092
• 期：1
• 页码：149-164
• 参考文献：1.Li, B., Schreck, T., Godil, A., et al.: SHREC’12 Track: Sketch-based 3D shape retrieval. In: Eurographics Workshop on 3D Object Retrieval 2012 (3DOR 2012) (2012)
  2.Funkhouser, T., Min, P., Kazhdan, M., et al.: A search engine for 3D models. ACM Trans. Graph. 22(1), 83–105 (2003)CrossRef
  3.Yoon, S.M., Kuijper, A.: Sketch-based 3D model retrieval using compressive sensing classification. Electron. Lett. 47(21), 1181–1183 (2011)CrossRef
  4.Li, B., Johan, H.: Sketch-based 3D model retrieval by incorporating 2D-3D alignment. Multimedia Tools Appl. 65(3), 363–385 (2013)CrossRef
  5.Liu, Q.: A Survey of Recent View-based 3D Model Retrieval Methods (2012)
  6.Saavedra, J.M., Bustos, B., Schreck, T., Yoon, S., Scherer, M.: Sketch-based 3D model retrieval using keyshapes for global and local representation. In: Proceedings of the 5th Eurographics Conference on 3D Object Retrieval, Cagliari, Italy, pp. 47–50. Eurographics Association (2012)
  7.Wang, F., Lin, L., Tang, M.: A new sketch-based 3D model retrieval approach by using global and local features. Graph. Models 76, 128–139 (2014)CrossRef
  8.Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)CrossRef
  9.Bay, H., Ess, A., Tuytelaars, T., Van, G.L.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110(3), 346–359 (2008)CrossRef
  10.Ohbuchi, R., Furuya, T.: Scale-weighted dense bag of visual features for 3D model retrieval from a partial view 3D model. In: 2009 IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), Kyoto, pp. 63–70 (2009)
  11.Furuya, T., Ohbuchi, R.: Visual saliency weighting and cross-domain manifold ranking for sketch-based image retrieval. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O’Connor, N. (eds.) MMM 2014. LNCS, vol. 8325, pp. 37–49. Springer, Heidelberg (2014). doi:10.​1007/​978-3-319-04114-8_​4 CrossRef
  12.Eitz, M., Richter, R., Boubekeur, T., Hildebrand, K., Alexa, M.: Sketch-based shape retrieval. ACM Trans. Grap. 31(4) (2012)
  13.He, J., Li, M., Tong, H., Zhang, C.: Manifold-ranking based image retrieval. In: Proceedings of MM 2004, pp. 9–16, 10–16 October 2004
  14.Tong, H., He, J., Li, M., et al.: Manifold-ranking-based keyword propagation for image retrieval. EURASIP J. Appl. Signal Process. (2006). (79412SI)
  15.Jin, H., He, R., Tao, W.: Multi-relationship based relevance feedback scheme in web image retrieval. Int. J. Innovative Comput. Inf. Control 4(6), 1315–1324 (2008)
  16.Guan, Z., Bu, J., Mei, Q., Chen, C., Wang, C.: Personalized tag recommendation using graph-based ranking on multi-type interrelated objects, pp. 540–547 (2009)
  17.Agarwal, S.: Ranking on graph data. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 25–32 (2006)
  18.Guan, Z., Bu, J., Mei, Q., Chen, C., Wang, C.: Music recommendation by unified hypergraph: combining social media information and music content. In: Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 540–547 (2009)
  19.Li, B., Li, Y., Li, C., et al.: SHREC’14 track: Extended large scale sketch-based 3D shape retrieval. In: Eurographics Workshop on 3D Object Retrieval, EG 3DOR (2014)
  20.Furuya, T., Ohbuchi, R.: Similarity metric learning for sketch-based 3D object retrieval. Multimedia Tools Appl. 74(23), 10367–10392 (2014)CrossRef
  21.Zhou, D.Y., Bousquet, O., Lal, T.N., Weston, J., Scholkopf, B.: Learning with local and global consistency. In: Advances in Neural Information Processing Systems, pp. 321–328 (2004)
  22.Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos, pp. 1470–1477 (2003)
  23.Eitz, M., Hays, J., Alexa, M.: How do humans sketch objects? ACM Trans. Graph. 31(4) (2012)
  24.Judd, T., Durand, F., Adelson, E.: Apparent ridges for line drawing. ACM Trans. Graph. 26(3), 19:1–19:8 (2007)CrossRef
  25.Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM International Conference on Image and Video Retrieval CIVR 2007, pp. 401–408. ACM, New York (2007)
  26.Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The Princeton shape benchmark, pp. 167–178 (2004)
  27.Justin, Z., Moffat, A.: Inverted files for text search engines. ACM Comput. Surv. (CSUR) 38(2) (2006). Article No. 6
  28.Wang, F., Kang, L., Li, Y.: Sketch-based 3D shape retrieval using convolutional neural networks. In: Computer Vision Foundation (2015)
  29.Chinen, T.T., Reed, T.R.: A performance analysis of fast gabor transform methods. Graph. Models Image Process. 59(3), 117–127 (1997)CrossRef
  
• 作者单位：Lu Qian (17) (18)
  Yachun Fan (17) (18)
  Mingquan Zhou (17) (18)
  Hua Luan (17) (18)
  Pu Ren (17) (18)
  
  17. College of Information Science and Technology, Beijing Normal University, Beijing, China
  18. Key Laboratory of Digital Protection and Virtual Reality for Cultural Heritage, Beijing, China
  
• 丛书名：Transactions on Edutainment XIII
• ISBN：978-3-662-54395-5
• 卷排序：10092

文摘

The demand for 3D model retrieval is increasing, and the sketch-based method has been proven to be the most effective and efficient approach to retrieve 3D models. The existing methods calculate distance based on feature extraction, showing its limitation in improving retrieval accuracy. Thus, a second ranking making use of relevance between features is a good way to go. In this paper, an extended manifold ranking method is presented as a new retrieval framework. Line drawings are abstracted to represent 3D models, and a visual vocabulary is used to describe the local features of both sketches and line drawings. To rank the similarities between models, a method of semantic classification as a constraint is presented. We use similarity weight to control the classification difference between models so that the ranking score of models that belong to the same class holds a higher similarity weight. Furthermore, based on the idea of manifold learning, a KNN algorithm is adopted to obtain better ranking results. Experiments on standard testing datasets have demonstrated that the proposed algorithm significantly improves the accuracy of 3D model retrieval and outperforms current state-of-the-art algorithms by comparison.