A New method for 3D Shape Indexing and Retrieval in Large Database by using the Level Cut

In this study, we propose a new method for indexing and retrieval of 3D models in large databases base d on binary images extracted from the 3D object called “ level cut” LC. These cuts are obtained by the inter section of the set of the plans with the 3D object. A set of e quidistant parallel plans generates by the intersec tion with the 3D object a set of cuts that used to indexing the 3D m odel. We are based on these cuts to describe the 3D object by using the vectors descriptors based on these cuts. To validate our descriptor we extract a test databa se from the NTU base. The robustness of our descriptor is well demonstrated by the comparison with the two will known descriptors, the 3D Zernike descriptor and the 3D i nvariant moment’s descriptor. The topological problem of the external surfaces that representing the 3D object h as been confronted, that shows the superiority of t he cut method, because it is keeping the external surfaces details of the 3D object during the cutting step.

[1]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[2]  Dietmar Saupe,et al.  Tools for 3D-object retrieval: Karhunen-Loeve transform and spherical harmonics , 2001, 2001 IEEE Fourth Workshop on Multimedia Signal Processing (Cat. No.01TH8564).

[3]  B. Kimia,et al.  3D object recognition using shape similiarity-based aspect graph , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[4]  Bo Li,et al.  Sketch-based 3D model retrieval by incorporating 2D-3D alignment , 2012, Multimedia Tools and Applications.

[5]  Kian-Ming Lim,et al.  Comparative Study of Hu Moments and Zernike Moments in Object Recognition , 2013, Smart Comput. Rev..

[6]  Pu Jiantao,et al.  3D model retrieval based on 2D slice similarity measurements , 2004 .

[7]  Agus Harjoko,et al.  Improved Real-Time Face Recognition based on three Level wavelet Decomposition-Principal Component Analysis and Mahalanobis Distance , 2014, J. Comput. Sci..

[8]  Nidhal K. El Abbadi,et al.  Fast Image Matching in Huge Database , 2014, J. Comput. Sci..

[9]  Yogendra Kumar Jain,et al.  Efficient view based 3-D object retrieval using Hidden Markov Model , 2013 .

[10]  Francoise Preteux,et al.  An overview of view-based 2D/3D indexing methods , 2010, Optical Engineering + Applications.

[11]  S. Muruganathan,et al.  Shape Retrieval through Mahalanobis Distance with Shortest Augmenting Path Algorithm , 2014, J. Comput. Sci..

[12]  Jan Flusser,et al.  Tensor Method for Constructing 3D Moment Invariants , 2011, CAIP.

[13]  Julie C. Mitchell,et al.  An Extension of 3D Zernike Moments for Shape Description and Retrieval of Maps Defined in Rectangular Solids , 2013 .

[14]  Weibin Liu,et al.  3D model retrieval based on 2D slice similarity measurements , 2004, Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004..

[15]  Agus Harjoko,et al.  Content based Batik Image Retrieval , 2014, J. Comput. Sci..

[16]  Mohamed Daoudi,et al.  3D Model Retrieval Based on Adaptive Views Clustering , 2005, ICAPR.

[17]  Atilla Baskurt,et al.  Generalizations of angular radial transform for 2D and 3D shape retrieval , 2005, Pattern Recognit. Lett..

[18]  Mohamed Daoudi,et al.  3D models retrieval by using characteristic views , 2002, Object recognition supported by user interaction for service robots.

[19]  Benjamin B. Kimia,et al.  3D Object Recognition Using Shape Similarity-Based Aspect Graph , 2001, ICCV.