Three-Dimensional Shape Recognition and Classification Using Local Features of Model Views and Sparse Representation of Shape Descriptors
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, a new algorithm is proposed for threedimensional (3D) shape recognition using local features ofmodel views and its sparse representation. The algorithm starts with the normalization of 3D models and theextraction of 2D views from uniformly distributed viewpoints. Consequently, the 2D views are stacked overeach other to from view cubes. The algorithm employs the descriptors of 3D local features in the view cubesafter applying Gabor filters in various directions as the initial features for 3D shape recognition. In the trainingstage, we store some 3D local features to build the prototype dictionary of local features. To extract an intermediatefeature vector, we measure the similarity between the local descriptors of a shape model and the localfeatures of the prototype dictionary. We represent the intermediate feature vectors of 3D models in the sparsedomain to obtain the final descriptors of the models. Finally, support vector machine classifiers are used torecognize the 3D models. Experimental results using the Princeton Shape Benchmark database showed theaverage recognition rate of 89.7% using 20 views. We compared the proposed approach with stateoftheartapproaches and the results showed the effectiveness of the proposed algorithm.
Abstract
In this paper, a new algorithm is proposed for threedimensional (3D) shape recognition using local features ofmodel views and its sparse representation. The algorithm starts with the normalization of 3D models and theextraction of 2D views from uniformly distributed viewpoints. Consequently, the 2D views are stacked overeach other to from view cubes. The algorithm employs the descriptors of 3D local features in the view cubesafter applying Gabor filters in various directions as the initial features for 3D shape recognition. In the trainingstage, we store some 3D local features to build the prototype dictionary of local features. To extract an intermediatefeature vector, we measure the similarity between the local descriptors of a shape model and the localfeatures of the prototype dictionary. We represent the intermediate feature vectors of 3D models in the sparsedomain to obtain the final descriptors of the models. Finally, support vector machine classifiers are used torecognize the 3D models. Experimental results using the Princeton Shape Benchmark database showed theaverage recognition rate of 89.7% using 20 views. We compared the proposed approach with stateoftheartapproaches and the results showed the effectiveness of the proposed algorithm.
참고문헌 (38)
- J. S. Nam, "Scenario-based 3D Objects Synthesizing System Design", Journal of Information Processing Systems, 2(1), pp.18~22 (2006)
- I. Atmosukarto, "3D shape analysis for quantification, classification, and retrieval", Ph. D., pp.2010
- J. W. Tangelder, "A survey of content based 3D shape retrieval methods", Multimedia Tools and Applications, 39 (2008)
- M. A. Savelonas, "An overview of partial 3D object retrieval methodologies", Multimedia Tools and Applications, 74, pp.11783~11808 (2015)
- C. Li, "Spatially aggregating spectral descriptors for nonrigid 3D shape retrieval : a comparative survey", Multimedia Systems, 20(3), pp.253~281 (2014)
- G. L. Lopez, "Comparative analysis of shape descriptors for 3D objects", Multimedia Tools and Applications, 76, pp.6993~7040 (2017)
- M. Elad, "Multimedia 2001", pp.107~118 (2002), Springer
- R. Osada, "Shape distributions", ACM Transactions on Graphics, 21(4), pp.807~832 (2002)
- R. Ohbuchi, "Shape-similarity search of 3D models by using enhanced shape functions", International Journal of Computer Applications in Technology, 23(2-4), pp.70~85 (2005)
- M. Mahmoudi, "Three-dimensional point cloud recognition via distributions of geometric distances", Graphical Models, 71(1), pp.22~31 (2009)
- D. Saupe, "Pattern Recognition", pp.392~397 (2001), Springer
- M. Kazhdan, "Rotation invariant spherical harmonic representation of 3D shape descriptors", Proceedings of Eurographics Symposium on Geometry Processing, pp.156~164 (2003)
- H. Laga, "Spherical wavelet descriptors for content-based 3D model retrieval", Proceedings of IEEE International Conference on Shape Modeling and Applications (2006)
- P. Shilane, "Distinctive regions of 3D surfaces", ACM Transactions on Graphics, 26(2) (2007)
- Y. Zhao, "Region-based saliency estimation for 3D shape analysis and understanding", Neurocomputing, 197, pp.1~13 (2016)
- I. Atmosukarto, "3D object classification using salient point patterns with application to craniofacial research", Pattern Recognition, 43(4), pp.1502~1517 (2010)
- I. Sipiran, "Harris 3D : a robust extension of the Harris operator for interest point detection on 3D meshes", The Visual Computer, 27(11) (2011)
- S. Bu, "Learning high-level feature by deep belief networks for 3-D model retrieval and recognition", IEEE Transactions on Multimedia, 16(8), pp.2154~2167 (2014)
- A. Flint, "Local 3D structure recognition in range images", IET Computer Vision, 2(4), pp.208~217 (2008)
- H. Sundar, "Skeleton based shape matching and retrieval", Proceedings of 2003 Shape Modeling International, pp.130~139 (2003)
- M. Hilaga, "Topology matching for fully automatic similarity estimation of 3D shapes", Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, pp.203~212 (2001)
- B. Leng, "A powerful 3D model classification mechanism based on fusing multi-graph", Neurocomputing, 168, pp.761~769 (2015)
- A. Kacem, "Image Analysis and Recognition", pp.181~188 (2013), Springer
- W. Mohamed, "Deformable 3D shape retrieval using a spectral geometric descriptor", Applied Intelligence, 45(2), pp.213~229 (2016)
- P. Daras, "A compact multi-view descriptor for 3D object retrieval", Proceedings of 2009 Seventh International Workshop on Content-Based Multimedia Indexing, pp.115~119 (2009)
- H. Su, "Multi-view convolutional neural networks for 3D shape recognition", Proceedings of the IEEE International Conference on Computer Vision, pp.945~953 (2015)
- K. Ding, "Computer Vision –ACCV 2012", pp.536~547 (2012), Springer
- S. Zhao, "View-based 3D object retrieval via multi-modal graph learning", Signal Processing, 112, pp.110~118 (2015)
- D. V. Vranic, "3D model retrieval", Proceedings of the Spring Conference on Computer Graphics and its Applications(SCCG2000), pp.89~93 (2000)
- D. V. Vranic, "Tools for 3D-object retrieval: Karhunen-Loeve transform and spherical harmonics", Proceedings of 2001 IEEE 4th Workshop on Multimedia Signal Processing, pp.293~298 (2001)
- P. Papadakis, "Efficient 3D shape matching and retrieval using a concrete radialized spherical projection representation", Pattern Recognition, 40(9), pp.2437~2452 (2007)
- J. Mutch, "Object class recognition and localization using sparse features with limited receptive fields", International Journal of Computer Vision, 80(1), pp.45~57 (2008)
- M. Aharon, "K-SVD : an algorithm for designing overcomplete dictionaries for sparse representation", IEEE Transactions on Signal Processing, 54(11), pp.4311~4322 (2006)
- H. Lee, "Efficient sparse coding algorithms", Advances in Neural Information Processing Systems, 20, pp.801~808 (2007)
- P. H. Chen, "A tutorial on ν-support vector machines", Applied Stochastic Models in Business and Industry, 21(2), pp.111~136 (2005)
- K. Siddiqi, "Retrieving articulated 3-D models using medial surfaces", Machine Vision and Applications, 19(4), pp.261~275 (2008)
- P. Shilane, "The princeton shape benchmark", Proceedings Shape Modeling Applications, pp.167~178 (2004)
- L. Hamid, "Supervised learning of salient 2D views of 3D models", The Journal of the Society for Art and Science, 7(4), pp.124~131 (2008)