Synonyms
Three dimensional descriptor
Definition
A 3D shape descriptor is a computational representation, in the form of a vector, of a set of points belonging to a surface. This set can span from a small local neighborhood of a point to the entire surface.
Background
The use of 3D descriptors stems from the need, in many 3D computer vision tasks, of measuring similarities between surfaces. By computing descriptionsof either single parts or the entire surface in the form of vectors, these can then be classified using machine learning tools, or matched by applying suitable metrics (e.g., Euclidean distance) so as to establish correspondences among surfaces. The theory of descriptors can be easily applied to all common representations of 3D data, such as point clouds, meshes, vowels, range images, etc. In addition, this process of translating the original 3D representation to the form of vectors is suitable for evaluating similarities between different kinds of 3D representations...
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bronstein AM, Bronstein MM, Bustos B, Castellani U, Crisani M, Falcidieno B, Guibas LJ, Kokkinos I, Murino V, Ovsjanikov M, Patané G, Sipiran I, Spagnuolo M, Sun J (2010) Shrec 2010: robust feature detection and description benchmark. EUROGRAPHICS workshop on 3D object retrieval (3DOR), European Association for Computer Graphics, Norrköping
Ovsjanikov M, Bronstein A, Bronstein M, Guibas L (2009) Shape google: a computer vision approach to isometry invariant shape retrieval. In: Computer vision workshops (ICCV Workshops), 2009 IEEE 12th international conference on, IEEE, Piscataway, pp 320–327
Shilane P, Min P, Kazhdan M, Funkhouser T (2004) The princeton shape benchmark. In: Proceedings of shape modeling international, IEEE Computer Society, Los Alamitos
Akgül CB, Sankur B, Yemez Y, Schmitt F (2009) 3D model retrieval using probability density-based shape descriptors. IEEE Trans Pattern Anal Mach Intel 31(6): 1117–1133
Kazhdan M, Funkhouser T, Rusinkiewicz S (2003) Rotation invariant spherical harmonic representation of 3D shape descriptors. In: Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on geometry processing, Eurographics/ACM SIGGRAPH, Aachen, pp 156–164
Tombari F, Salti S, Di Stefano L (2010) Unique signatures of histograms for local surface description. In: Proceedings of 11th European conference on computer vision (ECCV 10), Springer, Berlin
Johnson A, Hebert M (1999) Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Trans. on Pattern Analysis and Machine Intelligence, 21(5): 433–449
Frome A, Huber D, Kolluri R, Bülow T, Malik J (2004) Recognizing objects in range data using regional point descriptors. In: Proceedings of 8th European conference on computer vision (ECCV 04), Springer, Berlin, pp 224–237
Chua CS, Jarvis R (1997) Point signatures: a new representation for 3D object recognition. IJCV 25(1): 63–85
Zaharescu A, Boyer E, Varanasi K (2009) Surface feature detection and description with applications to mesh matching. In: International conference on computer vision and pattern recognition (CVPR), IEEE, Miami, Florida, USA
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Tombari, F. (2014). Three Dimensional Shape Descriptor. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_423
Download citation
DOI: https://doi.org/10.1007/978-0-387-31439-6_423
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30771-8
Online ISBN: 978-0-387-31439-6
eBook Packages: Computer ScienceReference Module Computer Science and Engineering