research-article

3D shape segmentation and labeling via extreme learning machine

Authors:

Yueshan XiongAuthors Info & Claims

SGP '14: Proceedings of the Symposium on Geometry Processing

Pages 85 - 95

https://doi.org/10.1111/cgf.12434

Published: 09 July 2014 Publication History

Abstract

We propose a fast method for 3D shape segmentation and labeling via Extreme Learning Machine (ELM). Given a set of example shapes with labeled segmentation, we train an ELM classifier and use it to produce initial segmentation for test shapes. Based on the initial segmentation, we compute the final smooth segmentation through a graph-cut optimization constrained by the super-face boundaries obtained by over-segmentation and the active contours computed from ELM segmentation. Experimental results show that our method achieves comparable results against the state-of-the-arts, but reduces the training time by approximately two orders of magnitude, both for face-level and super-face-level, making it scale well for large datasets. Based on such notable improvement, we demonstrate the application of our method for fast online sequential learning for 3D shape segmentation at face level, as well as realtime sequential learning at super-face level.

References

[1]

{BLVD11} Benhabiles H., Lavoué G., Vandeborre J.-P., Daoudi M.: Learning boundary edges for 3d-mesh segmentation. Computer Graphics Forum 30, 8 (2011), 2170--2182. 1, 2, 4, 8, 10

[2]

{BVZ01} Boykov Y., Veksler O., Zabih R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pat. Ana. & Mach. Int. 23, 11 (2001), 1222--1239. 5

Digital Library

[3]

{CGF09} Chen X., Golovinskiy A., Funkhouser T.: A benchmark for 3d mesh segmentation. ACM Trans. on Graph (SIGGRAPH) 28, 3 (2009), 73:1âĂŞ--73:12. 2, 5, 6, 7

Digital Library

[4]

{GF08} Golovinskiy A., Funkhouser T.: Randomized cuts for 3d mesh analysis. ACM Trans. on Graph (SIGGRAPH Asia) 27, 5 (2008), 145:1--145:12. 4

Digital Library

[5]

{GF09} Golovinskiy A., Funkhouser T.: Consistent segmentation of 3d models. Computers & Graphics 33, 3 (2009), 262--269. 8

Digital Library

[6]

{GHL14} Guo L., Hao J.-h., Liu M.: An incremental extreme learning machine for online sequential learning problems. Neurocomputing 128 (2014), 50--58. 10

Digital Library

[7]

{HFL12} Hu R., Fan L., Liu L.: Co-segmentation of 3d shapes via subspace clustering. Computer Graphics Forum 31, 5 (2012), 1703--1713. 1, 2, 5

Digital Library

[8]

{HKG11} Huang Q., Koltun V., Guibas L.: Joint shape segmentation with linear programming. 125:1--125:11. 1, 2, 4, 5

[9]

{HWL11} Huang G.-B., Wang D. H., Lan Y.: Extreme learning machines: a survey. International Journal of Machine Learning and Cybernetics 2, 2 (2011), 107--122. 1, 2, 9

[10]

{HZDZ12} Huang G.-B., Zhou H., Ding X., Zhang R.: Extreme learning machine for regression and multiclass classification. IEEE Trans. on Syst., Man, and Cybern. 42, 2 (2012), 513--529. 2, 3

Digital Library

[11]

{HZS06} Huang G.-B., Zhu Q.-Y., Siew C.-K.: Extreme learning machine: theory and applications. Neurocomputing 70, 1 (2006), 489--501. 2, 3

[12]

{KHS10} Kalogerakis E., Hertzmann A., Singh K.: Learning 3d mesh segmentation and labeling. ACM Trans. on Graph (SIGGRAPH) 29, 4 (2010), 102:1--102:12. 1, 2, 3, 5, 7, 8

Digital Library

[13]

{KT03} Katz S., Tal A.: Hierarchical mesh decomposition using fuzzy clustering and cuts. ACM Trans. on Graph (SIGGRAPH) 22, 3 (2003), 954--961. 4

Digital Library

[14]

{LHSS06} Liang N.-Y., Huang G.-B., Saratchandran P., Sundararajan N.: A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans. on Neural Networks 17, 6 (2006), 1411--1423. 3, 9

Digital Library

[15]

{MXLH12} Meng M., Xia J., Luo J., He Y.: Unsupervised co-segmentation for 3d shapes using iterative multi-label optimization. Computer-Aided Design 45, 2 (2012), 312--320. 2

Digital Library

[16]

{SSCO08} Shapira L., Shamir A., Cohen-Or D.: Consistent mesh partitioning and skeletonisation using the shape diameter function. The Visual Computer 24, 4 (2008), 249--259. 8

Digital Library

[17]

{SSS*10} Shapira L., Shalom S., Shamir A., Cohen-Or D., Zhang H.: Contextual part analogies in 3d objects. Int. J. Comp. Vis. 89, 2--3 (2010), 309--326. 4

Digital Library

[18]

{SvKK*11} Sidi O., Van Kaick O., Kleiman Y., Zhang H., Cohen-Or D.: Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering. ACM Trans. on Graph (SIGGRAPH Asia) 30, 6 (2011), 126:1--126:10. 1, 2

Digital Library

[19]

{vKTS*11} Van Kaick O., Tagliasacchi A., Sidi O., Zhang H., Cohen-Or D., Wolf L., Hamarneh G.: Prior knowledge for part correspondence. Computer Graphics Forum 30, 2 (2011), 553--562. 1, 2, 3, 7, 8

[20]

{WAvK*12} Wang Y., Asafi S., van Kaick O., Zhang H., Cohen-Or D., Chen B.: Active co-analysis of a set of shapes. ACM Trans. on Graph (SIGGRAPH Asia) 31, 6 (2012), 165:1--165:10. 1, 5, 6, 8

Digital Library

[21]

{XLZ*10} Xu K., Li H., Zhang H., Cohen-Or D., Xiong Y., Cheng Z.-Q.: Style-content separation by anisotropic part scales. ACM Trans. on Graph (SIGGRAPH Asia) 29, 6 (2010), 184:1--184:11. 2

Digital Library

Cited By

Shu ZLi SXin SLiu L(2025)3D Shape Segmentation With Potential Consistency Mining and EnhancementIEEE Transactions on Multimedia10.1109/TMM.2024.352167427(133-144)Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1109/TMM.2024.3521674
Shu ZWu TShen JXin SLiu L(2024)Semi-Supervised 3D Shape Segmentation via Self RefiningIEEE Transactions on Image Processing10.1109/TIP.2024.337420033(2044-2057)Online publication date: 12-Mar-2024
https://dl.acm.org/doi/10.1109/TIP.2024.3374200
Shu ZSun XPang CXin S(2024)3D Shape Segmentation via Attentive Nonuniform DownsamplingIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2024.343209534:12_Part_1(12184-12196)Online publication date: 1-Dec-2024
https://dl.acm.org/doi/10.1109/TCSVT.2024.3432095
Show More Cited By

Index Terms

3D shape segmentation and labeling via extreme learning machine
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Image segmentation
        Video segmentation

Recommendations

Automatic rib segmentation and sequential labeling via multi-axial slicing and 3D reconstruction
Abstract
Radiologists often inspect hundreds of two-dimensional computed-tomography (CT) images to accurately locate lesions and make diagnoses, by classifying and labeling the ribs. However, this task is repetitive and time consuming. To effectively ...
Progressive 3D shape segmentation using online learning

In this article, we propose a progressive 3D shape segmentation method, which allows users to guide the segmentation with their interactions, and does segmentation gradually driven by their intents. More precisely, we establish an online framework for ...
Semi-Supervised 3D Shape Segmentation via Self Refining
3D shape segmentation is a fundamental and crucial task in the field of image processing and 3D shape analysis. To segment 3D shapes using data-driven methods, a fully labeled dataset is usually required. However, obtaining such a dataset can be a ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

SGP '14: Proceedings of the Symposium on Geometry Processing

July 2014

293 pages

Conference Chairs:
Yu-Kun Lai
Cardiff University
,
Ralph R. Martin
Cardiff University

Sponsors

Disney Research Pixar: Disney Research Pixar
GeometryFactory: The Geometry Factory
ITN Insist: ITN Insist
Microsoft Reasearch: Microsoft Reasearch

Publisher

Eurographics Association

Goslar, Germany

Publication History

Published: 09 July 2014

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

30
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Shu ZLi SXin SLiu L(2025)3D Shape Segmentation With Potential Consistency Mining and EnhancementIEEE Transactions on Multimedia10.1109/TMM.2024.352167427(133-144)Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1109/TMM.2024.3521674
Shu ZWu TShen JXin SLiu L(2024)Semi-Supervised 3D Shape Segmentation via Self RefiningIEEE Transactions on Image Processing10.1109/TIP.2024.337420033(2044-2057)Online publication date: 12-Mar-2024
https://dl.acm.org/doi/10.1109/TIP.2024.3374200
Shu ZSun XPang CXin S(2024)3D Shape Segmentation via Attentive Nonuniform DownsamplingIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2024.343209534:12_Part_1(12184-12196)Online publication date: 1-Dec-2024
https://dl.acm.org/doi/10.1109/TCSVT.2024.3432095
Mu ALiu ZDuan GTan J(2023)Part-to-Surface Mesh Segmentation for Mechanical Models Based on Multi-Stage ClusteringComputer-Aided Design10.1016/j.cad.2023.103545162:COnline publication date: 1-Sep-2023
https://dl.acm.org/doi/10.1016/j.cad.2023.103545
Qiao YGao LYang JRosin PLai YChen X(2022)Learning on 3D Meshes With Laplacian Encoding and PoolingIEEE Transactions on Visualization and Computer Graphics10.1109/TVCG.2020.301444928:2(1317-1327)Online publication date: 1-Feb-2022
https://dl.acm.org/doi/10.1109/TVCG.2020.3014449
George DXie XLai YTam G(2022)A Deep Learning Driven Active Framework for Segmentation of Large 3D Shape CollectionsComputer-Aided Design10.1016/j.cad.2021.103179144:COnline publication date: 1-Mar-2022
https://dl.acm.org/doi/10.1016/j.cad.2021.103179
Wei HChen JZhu JYang XChu H(2022)A novel algorithm of Nested-ELM for predicting blasting vibrationEngineering with Computers10.1007/s00366-020-01082-z38:2(1241-1256)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.1007/s00366-020-01082-z
Yang JWang BWang MKe Y(2019)Unsupervised Co-segmentation of 3D Shapes Based on ComponentsProceedings of the 2nd International Conference on Computer Science and Software Engineering10.1145/3339363.3339386(89-95)Online publication date: 24-May-2019
https://dl.acm.org/doi/10.1145/3339363.3339386
Zhang YNiu L(2019)A Substructure Segmentation Method of Left Heart Regions from Cardiac CT Images Using Local Mesh Descriptors, Context and Spatial Location InformationPattern Recognition and Image Analysis10.1134/S105466181902010X29:2(230-239)Online publication date: 1-Apr-2019
https://dl.acm.org/doi/10.1134/S105466181902010X
Fang HWang XCai ZShi YSun XWu SZhou B(2019)Learning semantic abstraction of shape via 3D region of interestGraphical Models10.1016/j.gmod.2019.101038105:COnline publication date: 1-Sep-2019
https://dl.acm.org/doi/10.1016/j.gmod.2019.101038
Show More Cited By

View Options

View options

Figures

Tables

Media

View Table of Conten