Efficient view based 3-D object retrieval using Hidden Markov Model
Tóm tắt
Recent research effort has been dedicated to view based 3-D object retrieval, because of highly discriminative property of 3-D object and has multi view representation. The state-of-art method is highly depending on their own camera array setting for capturing views of 3-D object and use complex Zernike descriptor, HAC for representative view selection which limit their practical application and make it inefficient for retrieval. Therefore, an efficient and effective algorithm is required for 3-D Object Retrieval. In order to move toward a general framework for efficient 3-D object retrieval which is independent of camera array setting and avoidance of representative view selection, we propose an Efficient View Based 3-D Object Retrieval (EVBOR) method using Hidden Markov Model (HMM). In this framework, each object is represented by independent set of view, which means views are captured from any direction without any camera array restriction. In this, views are clustered (including query view) to generate the view cluster, which is then used to build the query model with HMM. In our proposed method, HMM is used in twofold: in the training (i.e. HMM estimate) and in the retrieval (i.e. HMM decode). The query model is trained by using these view clusters. The EVBOR query model is worked on the basis of query model combining with HMM. The proposed approach remove statically camera array setting for view capturing and can be apply for any 3-D object database to retrieve 3-D object efficiently and effectively. Experimental results demonstrate that the proposed scheme has shown better performance than existing methods.
Tài liệu tham khảo
Gao Y, Tang J, Hong R, Yan S, Dai Q, Zhang N and Chua T (2012) Camera Constrain-Free View-Based 3-D Object Retrieval, IEEE Transaction on Image Processing, 21: 2269–2281.
Bimbo A. D and Pala P. S (2006) Content-based retrieval of 3-D models, ACM Transactions on Multimedia Computing: Communications and Applications, 2: 20–43.
Tangelder J. W. H and Veltkamp R. C (2008) A survey of content based 3-D shape retrieval methods, Multimedia Tools Applications, 39: 441–471.
Leng B, Xiong Z and Fu X (2010) A 3-D shape retrieval framework for 3-D smart cities, Frontiers Computer Science in China, 4: 394–404.
Xiao Q, Wang H, Li F and Gao Y (2011) 3D object retrieval based on a graph model descriptor, Neurocomputing, 74: 3486–3493.
Gao Y, Wang M, Zha Z, Tian Q, Dai Q and Zhang N (2011) Less is more: Efficient 3-D object retrieval with query view selection, IEEE Transaction on Multimedia, 13: 1007–1018.
Yang Y, Lin H and Zhang Y (2007) Content-based 3-d model retrieval: A survey, IEEE Transaction on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 37: 1081–1098.
Akgul C. B, Sankur B, Yemez Y and Schmitt F (2010) Similarity learning for 3D object retrieval using relevance feedback and risk minimization, International Journal of Computer Vision, 89: 392–407.
Ip C, Lapadat D, Soeger L and Regli W. C (2002) Using shape distributions to compare solid models, Proceedings of the seventh ACM symposium on Solid modeling and applications, 273–280.
Johnson A. E and Hebert M (1999) Using spin images for efficient object recognition in cluttered 3-D scenes, IEEE Transaction on pattern analysis and machine intelligence, 21: 433–449.
Mademlis A, Daras P, Tzovaras D and Strintzis M.G (2009) 3D object retrieval using the 3-D shape impact descriptor, Pattern Recognition, 42: 2447–2459.
Paquet E, Murching A, Naveen T, Tabatabai A and Rioux M (2000) Description of shape information for 2-D and 3-D objects, Signal Processing: Image Communication, 16: 103–122.
Tangelder J and Veltkamp R (2002) Polyhedral model retrieval using weighted point sets, International Journal of Image and Graphics, 3: 209–229.
Osada R, Funkhouser T, Chazelle B and Dobkin D (2002) Shape distributions, ACM Transactions on Graphics, 21: 807–832.
Li F, Dai Q, Xu W and Er G (2009) Weighted subspace distance and its applications to object recognition and retrieval with image sets, IEEE Signal Processing Letters, 16: 227–230.
Gao Y, Yang Y, Dai Q and Zhang N (2010) Representative views re-ranking for 3-D model retrieval with multi-bipartite graph reinforcement model, Proceedings of the international conference on Multimedia, 947–950.
Li F, Dai Q, Xu W and Er G (2010) Statistical modeling and many-to-many matching for view-based 3-D object retrieval, Signal Processing: Image Communication, 25: 18–27.
Ohbuchi R, Osada K, Furuya T and Banno T (2008) Salient local visual features for shapebased 3-D model retrieval, IEEE Conference on Shape Modeling and Applications, 93–102.
Cheng M.-M, Zhang G.-X, Mitra N.J, Huang X and Hu S.-M (2011) Global contrast based salient region detection, IEEE Conference on Computer Vision and Pattern Recognition, 409–416.
Ji R, Yao H and Sun X (2011) Actor-independent action search using spatiotemporal vocabulary with appearance hashing, Pattern Recognition, 44: 624–638.
Chen D.Y, Tian X.P, Shen Y.T and Ouhyoung M (2003) On visual similarity based 3-D model retrieval, Computer Graphics Forum, 22: 223–232.
Shih J.L, Lee C.H and Wang J.T (2007) A new 3-D model retrieval approach based on the elevation descriptor, Pattern Recognition, Elsevier, 40:283–295.
Daras P and Axenopoulos A (2010) A 3-D shape retrieval framework supporting multimodal queries, International Journal of Computer Vision, 89: 229–247.
Rabiner R.L (1989) A Tutorial on Hidden Markov Models and Selected Applications, Proceedings of the IEEE in Speech Recognition, 77: 257–286.
Gao Y, Dai Q and Zhang N (2010) 3D model comparison using spatial structure circular descriptor, Pattern Recognition, Elsevier, 43: 1142–1151.
Papadakis P, Pratikakis I, Theoharis T and Perantonis S (2010) Panorama: A 3-D shape descriptor based on panoramic views for unsupervised 3-D object retrieval. In International Journal of Computer Vision, 89: 177–192.
Mahmoudi S and Daoudi M (2002) 3D models retrieval by using characteristic views, IEEE International Conference on Pattern Recognition, 2: 457–460.
Gao Y, Dai Q, Wang M and Zhang N (2011) 3D model retrieval using weighted bipartite graph matching, Signal Processing Image Communication, 26: 39–47.
Vranic D (2004) 3D Model Retrieval. Ph.D. dissertation: University at Leipzig. Institute for Informatics. Germany.
Ohbuchi R and Furuya T (2008) Accelerating bag-offeatures sift algorithm for 3-D model retrieval, Proceeding SAMT Workshop Semantic 3-D Media, 22–30.
Furuya T and Ohbuchi R (2008) Dense sampling and fast encoding for 3-D model retrieval using bag-of-visual features, Proceedings of the ACM International Conference on Image and Video Retrieval, 26.
Ohbuchi R and Furuya T (2009) Scale-weighted dense bag of visual features for 3-D model retrieval from a partial view 3-D model, IEEE Conference on Computer Vision Workshops, 63–70.
Ansary T. F, Daoudi M and Vandeborre J. P (2007) A Bayesian 3-D search engine using adaptive views clustering, IEEE Transaction on Multimedia, 9: 78–88.
Thomas A, Ferrari V, Leibe B, Tuytelaars T, Schiele B and Gool L. V (2006) Towards multi-view object class detection, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:1589–1596.
Savarese S and Fei-Fei L (2007) 3D generic object categorization, localization and pose estimation, IEEE International Conference on Computer Vision, 1–8.
Sun M, Su H, Savarese S and Fei-Fei L (2009) A multi-view probabilistic model for 3-D object classes, IEEE Conference on Computer Vision and Pattern Recognition, 1247–1254.
Bezdek J. C, Ehrlick R and Full W (1984) FCM: The fuzzy c-means clustering algorithm, Computer and Geosciences, Elsevier, 10: 191–203.
NTU 3D Model Benchmark ver. 1. http://3d.csie.ntu.edu.tw/~dynamic/benchmark/index.html Accessed 02 Mar 2013.
Vranic D (2003) An improvement of rotation invariant 3Dshape descriptor based on functions on concentric spheres, IEEE International Conference on Image Processing, 3: 757–760.
Ji R, Duan L.-Y, Chen J, Yao H, Yuan J, Rui Y and Gao W (2012) Location discriminative vocabulary coding for mobile landmark search, International Journal of Computer Vision, 96: 290–314.