Multimodal Feature Fusion for 3D Shape Recognition and Retrieval

Three-dimensional shapes contain different kinds of information that jointly characterize the shape. Traditional methods, however, perform recognition or retrieval using only one type. This article presents a 3D feature learning framework that combines different modality data effectively to promote the discriminability of unimodal features. Two independent deep belief networks (DBNs) are employed to learn high-level features from low-level features, and a restricted Boltzmann machine (RBM) is trained for mining the deep correlations between the different modalities. Experiments demonstrate that the proposed method can achieve better performance.

[1]  Afzal Godil,et al.  Visual Similarity Based 3D Shape Retrieval Using Bag-of-Features , 2010, 2010 Shape Modeling International Conference.

[2]  Junwei Han,et al.  Shift-invariant ring feature for 3D shape , 2014, The Visual Computer.

[3]  Hamid Laga,et al.  Geometry and context for semantic correspondences and functionality recognition in man-made 3D shapes , 2013, TOGS.

[4]  Ming Ouhyoung,et al.  3D Model Search Engine Based on Lightfield Descriptors , 2003, Eurographics.

[5]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[6]  Umberto Castellani,et al.  Sparse points matching by combining 3D mesh saliency with statistical descriptors , 2008, Comput. Graph. Forum.

[7]  Remco C. Veltkamp,et al.  A survey of content based 3D shape retrieval methods , 2004, Proceedings Shape Modeling Applications, 2004..

[8]  Hamid Laga.  Semantics-Driven Approach for Automatic Selection of Best Views of 3D Shapes , 2010, 3DOR@Eurographics.

[9]  Zhang Xiong,et al.  3D Object Classification Using Deep Belief Networks , 2014, MMM.

[10]  Leonidas J. Guibas,et al.  Shape google: Geometric words and expressions for invariant shape retrieval , 2011, TOGS.

[11]  Ryutarou Ohbuchi,et al.  Dense sampling and fast encoding for 3D model retrieval using bag-of-visual features , 2009, CIVR '09.

[12]  A. Bronstein,et al.  Learning Spectral Descriptors for Deformable Shape Correspondence , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[14]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[15]  Leonidas J. Guibas,et al.  A concise and provably informative multi-scale signature based on heat diffusion , 2009 .

[16]  Vincent Barra,et al.  Learning Kernels on Extended Reeb Graphs for 3D Shape Classification and Retrieval , 2013, 3DOR@Eurographics.

[17]  Kun Zhou,et al.  A Survey on Partial Retrieval of 3D Shapes , 2013, Journal of Computer Science and Technology.

[18]  Iasonas Kokkinos,et al.  Scale-invariant heat kernel signatures for non-rigid shape recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.