article

Shape distributions

Authors:

Thomas Funkhouser,

Bernard Chazelle,

David DobkinAuthors Info & Claims

ACM Transactions on Graphics (TOG), Volume 21, Issue 4

Pages 807 - 832

https://doi.org/10.1145/571647.571648

Published: 01 October 2002 Publication History

Abstract

Measuring the similarity between 3D shapes is a fundamental problem, with applications in computer graphics, computer vision, molecular biology, and a variety of other fields. A challenging aspect of this problem is to find a suitable shape signature that can be constructed and compared quickly, while still discriminating between similar and dissimilar shapes.In this paper, we propose and analyze a method for computing shape signatures for arbitrary (possibly degenerate) 3D polygonal models. The key idea is to represent the signature of an object as a shape distribution sampled from a shape function measuring global geometric properties of an object. The primary motivation for this approach is to reduce the shape matching problem to the comparison of probability distributions, which is simpler than traditional shape matching methods that require pose registration, feature correspondence, or model fitting.We find that the dissimilarities between sampled distributions of simple shape functions (e.g., the distance between two random points on a surface) provide a robust method for discriminating between classes of objects (e.g., cars versus airplanes) in a moderately sized database, despite the presence of arbitrary translations, rotations, scales, mirrors, tessellations, simplifications, and model degeneracies. They can be evaluated quickly, and thus the proposed method could be applied as a pre-classifier in a complete shape-based retrieval or analysis system concerned with finding similar whole objects. The paper describes our early experiences using shape distributions for object classification and for interactive web-based retrieval of 3D models.

References

[1]

Aherne, F., Thacker, N., and Rockett, P. 1997. Optimal pairwise geometric histograms. BMVC, 480--490.]]

[2]

Alt, H. and Guibas, L. J. 1996. Discrete geometric shapes: Matching, interpolation, and approximation: A survey. Tech. Rep. B 96-11, EVL-1996-142, Institute of Computer Science, Freie Universität Berlin.]]

[3]

Amit, Y., Grenander, U., and Piccioni, M. 1991. Structural image restoration through deformable templates. J. Am. Statistical Assn. 86, 440, 376--387.]]

[4]

Ankerst, M., Kastenmüller, G., Kriegel, H.-P., and Seidl, T. 1999. Nearest neighbor classification in 3d protein databases. ISMB.]]

[5]

Ashbrook, A., Thacker, N. A., Rockett, P. I., and Brown, C. I. 1995a. Robust recognition of scaled shapes using pairwise geometric histograms. BMVC, 503--512.]]

[6]

Arbter, K., Snyder, W. E., Burkhardt, H., and Hirzinger, G. 1990. Application of affine-invariant Fourier descriptors to recognition of 3-D objects. IEEE Trans. Pattern Anal. Mach. Intell. 12, 7 (July), 640--647.]]

[7]

Arkin, E. M., Chew, L. P., Huttenlocher, D. P., Kedem, K., and Mitchell, J. S. 1991. An efficiently computable metric for comparing polygonal shapes. IEEE Trans. Pattern Anal. Mach. Intell. 13, 3 (March), 209--216.]]

[8]

Arman, F. and Aggarwal, J. 1993. Model-based object recognition in dense-range images---a review. ACM Comput. Surv. 25, 1, 5--43.]]

[9]

Ashbrook, A., Rockett, P., and Thacker, N. 1995b. Multiple shape recognition using pairwise geometric histogram based algortihms. IEEE Image Processing.]]

[10]

Ashbrook, A., Thacker, N., and Rockett, P. 1995c. Pairwise geometric histograms: A scaleable solution for recognition of 2d rigid shapes. 9th SCIA 1, 271--278.]]

[11]

Bardinet, E., Vidal, S. F., Arroyo, S. D., Malandain, G., and de la Blanca Capilla, N. P. 2000. Structural object matching. Tech. Rep. DECSAI-000303, Dept. of Computer Science and AI, University of Granada, Spain. February.]]

[12]

Barequet, G. and Kumar, S. 1997. Repairing CAD models. IEEE Visualization '97, 363--370.]]

[13]

Basri, R., Costa, L., Geiger, D., and Jacobs, D. 1998. Determining the similarity of deformable shapes. Vision Research 38, 2365--2385.]]

[14]

Belongie, S., Malik, J., and Puzicha, J. 2001. Matching shapes. ICCV.]]

[15]

Besl, P. 1995. Triangles as a primary representation. Object Recognition in Computer Vision LNCS 994, 191--206.]]

[16]

Besl, P. J. and Jain, R. C. 1985. Three-dimensional object recognition. Comput. Surv. 17, 1 (March), 75--145.]]

[17]

Bhattacharyya, A. 1943. On a measure of divergence between two statistical populations defined by their probability distributions. Bulletin of the Calcutta Mathematics Society 35, 99--110.]]

[18]

Binford, T. 1971. Visual perception by computer. IEEE Conference on Systems Science and Cybernetics.]]

[19]

Bloomenthal, J. and Lim, C. 1999. Skeletal methods of shape manipulation. Shape Modeling and Applications, 44--47.]]

[20]

Carlsson, S. 1999. Order structure, correspondence, and shape based categories. Shape, Contour and Grouping in Computer Vision, 58--71.]]

[21]

Chang, S. and Smith, J. 1995. Extracting multi-dimensional signal features for content-based visual query. SPIE Symposium on Visual Communications and Signal Processing 2501, 2 (May), 995--1006.]]

[22]

Chen, J. 2001. The Search for 3D Models. Junior Independent Work, Computer Science Department, Princeton University.]]

[23]

Cohen, J., Varshney, A., Manocha, D., Turk, G., Weber, H., Agarwal, P., Frederick P. Brooks, Jr., and Wright, W. 1996. Simplification envelopes. SIGGRAPH, 119--128.]]

[24]

Delingette, H., Hebert, M., and Ikeuchi, K. 1992. Shape representation and image segmentation using deformable surfaces. Image and Vision Computing 10, 3 (April), 132--144.]]

[25]

Delingette, H., Hebert, M., and Ikeuchi, K. 1993. A spherical representation for the recognition of curved objects. ICCV, 103--112.]]

[26]

Duda, R., Hart, P., and Stork, D. 2001. Pattern Classification, Second Edition. John Wiley & Sons, New York.]]

[27]

Elad, M., Tal, A., and Ar, S. 2001. Content based retrieval of VRML objects---an iterative and interactive approach. The 6th Eurographics Workshop in Multimedia, Manchester, U.K.]]

[28]

Evans, A., Thacker, N., and Mayhew, J. 1992. Pairwise representation of shape. 11th ICPR 1. 133--136.]]

[29]

Evans, A., Thacker, N., and Mayhew, J. 1993. The use of geometric histograms for model-based object recognition. 4th BMVC, 429--438.]]

[30]

Flickner, M., Sawhney, H., Niblack, W., Ashley, J., and Huang, Q. 1995. Query by image and video content: the qbic system. IEEE Comput. 28, 9, 23--32.]]

[31]

Gain, J. and Scott, J. 1999. Fast polygon mesh querying by example. SIGGRAPH Technical Sketches.]]

[32]

Gueziec, A., Taubin, G., Lazarus, F., and Horn, W. 1998. Converting sets of polygons to manifold surfaces by cutting and stitching. IEEE Visualization '98, 383--390.]]

[33]

Helgason, S. 1999. The radon transform. Progress in Mathematics, Springer, 2nd ed. 5.]]

[34]

Holm, L. and Sander, C. 1998. Touring protein fold space with dali/fssp. Nucleic Acids Research 26, 316--319.]]

[35]

Horn, B. 1984. Extended gaussian images. Proc. of the IEEE 72, 12 (December), 1671--1686.]]

[36]

Huet, B. and Hancock, E. 1996. Structural indexing of infra-red images using statistical histogram comparison. IWISP, 653--656.]]

[37]

Igarashi, T., Matsuoka, S., and Tanaka, H. 1999. Teddy: A sketching interface for 3d freeform design. SIGGRAPH, 409--416. ISBN 0-20148-560-5. Held in Los Angeles, California.]]

[38]

Ikeuchi, K., Shakunaga, T., Wheeler, M., and Yamazaki, T. 1996. Invariant histograms and deformable template matching for sar target recognition. Computer Vision and Pattern Recognition.]]

[39]

Jacobs, C., Finkelstein, A., and Salesin, D. 1995. Fast multiresolution image querying. SIGGRAPH, 277--286.]]

[40]

Jain, A., Zhong, Y., and Lakshmanan, S. 1996. Object matching using deformable templates. IEEE Trans. Pattern Anal. Mach. Intell. 18, 3, 267--278.]]

[41]

Johnson, A. E. and Hebert, M. 1999. Using spin-images for efficient multiple model recognition in cluttered 3-d scenes. IEEE PAMI 21, 5, 433--449.]]

[42]

Kullback, S. 1968. Information Theory and Statistics. Dover.]]

[43]

Stanford University Computer Graphics Laboratory 1996. http://graphics.stanford.edu/data.]]

[44]

Lamdam, Y. and Wolfson, H. 1988. Geometric hashing: a general and efficient model-based recognition scheme. ICCV.]]

[45]

Lin, Y., Dou, J., and Wang, H. 1992. Contour shape description based on an arch height function. Pattern Recognition 25, 17--23.]]

[46]

Loncaric, S. 1998. A survey of shape analysis techniques. Pattern Recognition 31, 8, 983--1001.]]

[47]

Mori, G., Belongie, S., and Malik, J. 2001. Shape contexts enable efficient retrieval of similar shapes. CVPR.]]

[48]

Murali, T. and Funkhouser, T. 1997. Consistent solid and boundary representations from arbitrary polygonal data. Computer Graphics (1997 SIGGRAPH Symposium on Interactive 3D Graphics), 155--162.]]

[49]

Ogle, V. and Stonebraker, M. 1995. Chabot: Retrieval from a relational database of images. IEEE Computer 28, 9, 40--48.]]

[50]

Pentland, A. and Sclaroff, S. 1991. Closed-form solutions for physically based shape modeling and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 13, 7, 715--729.]]

[51]

Pope, A. R. 1994. Model-based object recognition: A survey of recent research. Tech. Rep. TR-94-04, University of British Columbia. January.]]

[52]

Prokop, R. J. and Reeves, A. P. 1992. A survey of moment-based techniques for unoccluded object representation and recognition. CVGIP: Graphics Models and Image Processsing 54, 5, 438--460.]]

[53]

Puzicha, J., Rubner, Y., Tomasi, C., and Buhmann, J. M. 1999. Empirical evaluation of dissimilarity measures for color and texture. IEEE International Conference on Computer Vision, 1165--1173.]]

[54]

Rann, A. G. and Katsevich, A. I. 1996. The Radon Transform and Local Tomography. CRC Press.]]

[55]

Riocreux, P., Thacker, N., and Yates, R. 1994. An analysis of pairwise geometric histograms for view-based object recognition. BMVC.]]

[56]

Rubner, Y., Tomasi, C., and Guibas, L. 1998. A metric for distributions with applications to image databases. 6th ICCV, 59--66.]]

[57]

Sclaroff, S. and Pentland, A. 1995. Modal matching for correspondence and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 17, 6 (June), 545--561.]]

[58]

Shen, H. C. and Wong, A. K. C. 1983. Generalized texture representation and metric. Computer, Vision, Graphics, and Image Processing 23, 187--206.]]

[59]

Siddiqi, K., Shokoufandeh, A., Dickinson, S. J., and Zucker, S. W. 1998. Shock graphs and shape matching. Computer Vision, 222--229.]]

[60]

Skiena, S., Smith, W., and Lemke, P. 1990. Reconstructing sets from interpoint distances. Proceedings of the Sixth Annual Symposium on Computational Geometry, 332--339.]]

[61]

Solina, F. and Bajcsy, R. 1990. Recovery of parametric models from range images: The case for superquadrics with global deformations. Pattern Anal. Mach. Intell. 12, 2 (February), 131-- 147.]]

[62]

Storti, D., Turkiyyah, G., Ganter, M., Lim, C., and Stal, D. 1997. Skeleton-based modeling operations on solids. Solid Modeling, 141--154.]]

[63]

Tappert, C. 1982. Cursive script recognition by elastic matching. IBM Res. Develop. 26, 6, 765--771.]]

[64]

Taubin, G. and Cooper, D. 1992. Geometric Invariance in Computer Vision. MIT Press, Chapter Object recognition based on moment (of algebraic) invariants.]]

[65]

Terzopoulos, D. and Metaxas, D. 1991. Dynamic 3d models with local and global deformations: Deformable superquadrics. IEEE Trans. Pattern Anal. and Mach. Intell. 13, 7, 703--714.]]

[66]

Thacker, N., Riocreux, P., and Yates, R. 1995. Assessing the completeness properties of pairwise geometric histograms. Image and Vision Computing 13, 5, 423--429.]]

[67]

Tsai, W. and Yu, S. 1985. Attributive string matching with merging for shape recognition. IEEE Trans. Pattern Anal. Mach. Intell. 7, 453--462.]]

[68]

Uras, C. and Verri, A. 1994. On the recognition of the alphabet of the sign language through size functions. IAPR, 334--338.]]

[69]

Uras, C. and Verri, A. 1997. Computing size functions from edge maps. Int. J. Comput. Vis. 23, 2, 169--183.]]

[70]

Veltkamp, R. C. and Hagedoorn, M. 1999. State-of-the-art in shape matching. Tech. Rep. UU-CS-1999-27, Utrecht University, the Netherlands.]]

[71]

Werman, M., Peleg, S., and Rosenfeld, A. 1985. A distance metric for multi-dimensional histograms. Computer, Vision, Graphics, and Image Processing 32, 328--336.]]

[72]

Wu, K. and Levine, M. 1994. Recovering parametrics geons from multiview range data. CVPR, 159--166.]]

[73]

Young, I., Walker, J., and Bowie, J. 1974. An analysis technique for biological shape. Computer Graphics and Image Processing 25, 357--370.]]

[74]

Zhang, D. and Hebert, M. 1999. Harmonic maps and their applications in surface matching. IEEE Conference on Computer Vision and Pattern Recognition (CVPR '99).]]

Cited By

Zhao YDeng JGao QZhang X(2024)SGRTmreg: A Learning-Based Optimization Framework for Multiple Pairwise RegistrationsSensors10.3390/s2413414424:13(4144)Online publication date: 26-Jun-2024
https://doi.org/10.3390/s24134144
Volkau IKrasovskii SMujeeb ABalinsky H(2024)Computer Vision Approach in Monitoring for Illicit and Copyrighted Objects in Digital ManufacturingComputers10.3390/computers1304009013:4(90)Online publication date: 28-Mar-2024
https://doi.org/10.3390/computers13040090
Rui LPeng Q(2024)Feature Skeletons-Based Model Retrieval for Bolus Shaping in Cancer Care2024 9th International Conference on Smart and Sustainable Technologies (SpliTech)10.23919/SpliTech61897.2024.10612542(1-6)Online publication date: 25-Jun-2024
https://doi.org/10.23919/SpliTech61897.2024.10612542
Show More Cited By

Index Terms

Shape distributions
1. Computing methodologies

Recommendations

Ricci Flow for 3D Shape Analysis

Ricci flow is a powerful curvature flow method, which is invariant to rigid motion, scaling, isometric, and conformal deformations. We present the first application of surface Ricci flow in computer vision. Previous methods based on conformal geometry, ...
2D-Shape Analysis Using Conformal Mapping

The study of 2D shapes and their similarities is a central problem in the field of vision. It arises in particular from the task of classifying and recognizing objects from their observed silhouette. Defining natural distances between 2D shapes creates ...
Pairwise Harmonics for Shape Analysis

This paper introduces a simple yet effective shape analysis mechanism for geometry processing. Unlike traditional shape analysis techniques which compute descriptors per surface point up to certain neighborhoods, we introduce a shape analysis framework ...

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Graphics

ACM Transactions on Graphics Volume 21, Issue 4

October 2002

84 pages

ISSN:0730-0301

EISSN:1557-7368

DOI:10.1145/571647

Issue’s Table of Contents

Copyright © 2002 ACM.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 October 2002

Published in TOG Volume 21, Issue 4

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1,360
Total Citations
View Citations
5,551
Total Downloads

Downloads (Last 12 months)241
Downloads (Last 6 weeks)18

Reflects downloads up to 02 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Zhao YDeng JGao QZhang X(2024)SGRTmreg: A Learning-Based Optimization Framework for Multiple Pairwise RegistrationsSensors10.3390/s2413414424:13(4144)Online publication date: 26-Jun-2024
https://doi.org/10.3390/s24134144
Volkau IKrasovskii SMujeeb ABalinsky H(2024)Computer Vision Approach in Monitoring for Illicit and Copyrighted Objects in Digital ManufacturingComputers10.3390/computers1304009013:4(90)Online publication date: 28-Mar-2024
https://doi.org/10.3390/computers13040090
Rui LPeng Q(2024)Feature Skeletons-Based Model Retrieval for Bolus Shaping in Cancer Care2024 9th International Conference on Smart and Sustainable Technologies (SpliTech)10.23919/SpliTech61897.2024.10612542(1-6)Online publication date: 25-Jun-2024
https://doi.org/10.23919/SpliTech61897.2024.10612542
ZHANG KZHANG SWEI SZHOU YXIONG J(2024)An efficient assembly retrieval method based on compressed part parameter vectorsJournal of Advanced Mechanical Design, Systems, and Manufacturing10.1299/jamdsm.2024jamdsm005318:5(JAMDSM0053-JAMDSM0053)Online publication date: 2024
https://doi.org/10.1299/jamdsm.2024jamdsm0053
Jiménez-Badillo DMendoza-Montoya ORuiz-Correa S(2024)Application of computer vision techniques for 3D matching and retrieval of archaeological objectsF1000Research10.12688/f1000research.127095.212(182)Online publication date: 25-Mar-2024
https://doi.org/10.12688/f1000research.127095.2
Dou WSun JNiu DPeng J(2024)AdaBoost-Based 3D Object Classification from Surface and Depth Map DescriptorsProceedings of the 2024 16th International Conference on Machine Learning and Computing10.1145/3651671.3651716(441-446)Online publication date: 2-Feb-2024
https://dl.acm.org/doi/10.1145/3651671.3651716
Nakai SKitanishi TMizuseki K(2024)Distinct manifold encoding of navigational information in the subiculum and hippocampusScience Advances10.1126/sciadv.adi447110:5Online publication date: 2-Feb-2024
https://doi.org/10.1126/sciadv.adi4471
Zhang CWang YWu QZheng JYang JQuan SZhang Y(2024)Multi-scale point pair normal encoding for local feature description and 3D object recognitionJournal of Electronic Imaging10.1117/1.JEI.33.4.04300533:04Online publication date: 1-Jul-2024
https://doi.org/10.1117/1.JEI.33.4.043005
Wu HFang LYu QYang C(2024)Learning Robust Point Representation for 3D Non-Rigid Shape RetrievalIEEE Transactions on Multimedia10.1109/TMM.2023.332315426(4430-4444)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TMM.2023.3323154
Liu ALu HZhou HLi TKankanhalli M(2024)Balanced Class-Incremental 3D Object Classification and RetrievalIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2023.328403236:1(35-48)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TKDE.2023.3284032
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents