Segmentation of 3D meshes combining the artificial neural network classifier and the spectral clustering
Автор: Zakani Fatima Rafii, Arhid Khadija, Bouksim Mohcine, Aboulfatah Mohamed, Gadi Taoufiq
Журнал: Компьютерная оптика @computer-optics
Рубрика: Обработка изображений, распознавание образов
Статья в выпуске: 2 т.42, 2018 года.
Бесплатный доступ
3D mesh segmentation has become an essential step in many applications in 3D shape analysis. In this paper, a new segmentation method is proposed based on a learning approach using the artificial neural networks classifier and the spectral clustering for segmentation. Firstly, a training step is done using the artificial neural network trained on existing segmentation, taken from the ground truth segmentation (done by humane operators) available in the benchmark proposed by Chen et al. to extract the candidate boundaries of a given 3D-model based on a set of geometric criteria. Then, we use this resulted knowledge to construct a new connectivity of the mesh and use the spectral clustering method to segment the 3D mesh into significant parts. Our approach was evaluated using different evaluation metrics. The experiments confirm that the proposed method yields significantly good results and outperforms some of the competitive segmentation methods in the literature.
3d shapes, segmentation, artificial neural networks, spectral clustering
Короткий адрес: https://sciup.org/140228732
IDR: 140228732 | DOI: 10.18287/2412-6179-2018-42-2-312-319
Список литературы Segmentation of 3D meshes combining the artificial neural network classifier and the spectral clustering
- Attene, M. Mesh segmentation -A comparative study/M. Attene, S. Katz, M. Mortara, G. Patane, M. Spagnuolo, A. Tal//IEEE International Conference on Shape Modeling and Applications 2006 (SMI’06). -2006. -7. - DOI: 10.1109/SMI.2006.24
- Shamir, A. A survey on mesh segmentation techniques/A. Shamir//Computer Graphics Forum. -2008. -Vol. 27, Issue 6. -P. 1539-1556. - DOI: 10.1111/j.1467-8659.2007.01103.x
- Theologou, P. A comprehensive overview of methodologies and performance evaluation frameworks in 3D mesh segmentation/P. Theologou, I. Pratikakis, T. Theoharis//Computer Vision and Image Understanding. -2015. -Vol. 135. -P. 49-82. - DOI: 10.1016/j.cviu.2014.12.008
- Chahhou, M. Segmentation of 3D meshes using p-spectral clustering/M. Chahhou, L. Moumoun, M. El Far, T. Gadi//IEEE Transactions on Pattern Analysis and Machine Intelligence. -2014. -Vol. 36, Issue 8. -P. 1687-1693. - DOI: 10.1109/TPAMI.2013.2297314
- Khadija, A. An efficient hierarchical 3D mesh segmentation using negative curvature and dihedral angle/A. Khadija, F.R. Zakani, M. Bouksim, M. Aboulfatah, T. Gadi//International Journal of Intelligent Engineering and Systems. -2017. -Vol. 10, Issue 5. -P. 143-152. - DOI: 10.22266/ijies2017.1031.16
- Benhabiles, H. Learning boundary edges for 3D-mesh segmentation/H. Benhabiles, G. Lavoué, J.P. Vandeborre, M. Daoudi//Computer Graphics Forum. -2011. -Vol. 30, Issue 8. -P. 2170-2182. - DOI: 10.1111/j.1467-8659.2011.01967.x
- Yang, F. A fast and efficient mesh segmentation method based on improved region growing/F. Yang, F. Zhou, R. Wang, L. Liu, X. Luo//Applied Mathematics -A Journal of Chinese Universities. -2014. -Vol. 29, Issue 4. -P. 468-480. - DOI: 10.1007/s11766-014-3240-0
- Zuckerberger, E. Polyhedral surface decomposition with applications/E. Zuckerberger, A. Tal, S. Shlafman//Computers & Graphics. -2002. -Vol. 26, Issue 5. -P. 733-743. - DOI: 10.1016/S0097-8493(02)00128-0
- Chen, L. An efficient and robust algorithm for 3D mesh segmentation/L. Chen, N.D. Georganas//Multimedia Tools and Applications. -2006. -Vol. 29, Issue 2. -P. 109-125. - DOI: 10.1007/s11042-006-0002-x
- Shlafman, S. Metamorphosis of polyhedral surfaces using decomposition/S. Shlafman, A. Tal, S. Katz//Computer Graphics Forum. -2002. -Vol. 21. -P. 219-228. - DOI: 10.1111/1467-8659.00581
- Liu, R. Segmentation of 3D meshes through spectral clustering/R. Liu, H. Zhang//Proceedings of the 12th Pacific Conference on Computer Graphics and Applications. -2004. -P. 298-305. - DOI: 10.1109/PCCGA.2004.1348360
- Asafi, S. Weak convex decomposition by lines-of-sight/S. Asafi, A. Goren, D. Cohen-Or//Computer Graphics Forum. -2013. -Vol. 32, Issue 5. -P. 23-31. - DOI: 10.1111/cgf.12169
- Hoffman, D.D. Parts of reCognition/D.D. Hoffman, W.A. Richards//Cognition. -1984. -Vol. 18, Issue 1-3. -P. 65-96. - DOI: 10.1016/0010-0277(84)90022-2
- Theologou, P. Unsupervised spectral mesh segmentation driven by heterogeneous graphs/P. Theologou, I. Pratikakis, T. Theoharis//IEEE Transactions on Pattern Analysis and Machine Intelligence. -2017. -Vol. 39, Issue 2. -P. 397-410. - DOI: 10.1109/TPAMI.2016.2544311
- Kalogerakis, E. Learning 3D mesh segmentation and labeling/E. Kalogerakis, A. Hertzmann, K. Singh//ACM Transactions on Graphics. -2010. -Vol. 29, Issue 4. -102. - DOI: 10.1145/1833349.1778839
- Lv, J. Semi-supervised mesh segmentation and labeling/J. Lv, X. Chen, J. Huang, H. Bao//Computer Graphics Forum. -2012. -Vol. 31, Issue 7. -P. 2241-2248. - DOI: 10.1111/j.1467-8659.2012.03217.x
- Lippmann, R.P. Pattern classification using neural networks/R.P. Lippmann//IEEE Communications Magazine. -1989. -Vol. 27, Issue 11. -P. 47-50. - DOI: 10.1109/35.41401
- Neurocomputing: Foundations of research/Ed. by J.A. Anderson, E. Rosenfeld. -Cambridge: MIT Press, 1988. -752 p. -ISBN: 978-0-262-01097-9.
- Kohonen, T. Neural Modeling/T. Kohonen. -In Book: Kohonen, T. Self-organizing maps/T. Kohonen. -Berlin, Heidelberg: Springer-Verlag, 2001. -P. 71-104. - DOI: 10.1007/978-3-642-56927-2_2
- Bühler, T. Spectral Clustering based on the graph p-Laplacian/T. Bühler, M. Hein//ICML ’09 Proceedings of the 26th Annual International Conference on Machine Learning. -2009. -Vol. 382. -P. 11-88. - DOI: 10.1145/1553374.1553385
- Ng, A.Y. On spectral clustering: analysis and an algorithm/A.Y. Ng, M.I. Jordan, Y. Weiss//Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic. -2001. -P. 849-856.
- Hagen, L. New spectral methods for ratio cut partitioning and clustering/L. Hagen, A.B. Kahng//IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. -1992. -Vol. 11, Issue 9. -P. 1074-1085. - DOI: 10.1109/43.159993
- Shi, J. Normalized cuts and image segmentation/J. Shi, J. Malik//IEEE Transactions on Pattern Analysis and Machine Intelligence. -2000. -Vol. 22, Issue 8. -P. 888-905. - DOI: 10.1109/34.868688
- Amghibech, S. Eigenvalues of the discrete p-Laplacian for graphs/S. Amghibech//Ars Combinatoria. -2003. -Vol. 67. -P. 283-302.
- Shapira, L. Consistent mesh partitioning and skeletonisation using the shape diameter function/L. Shapira, A. Shamir, D. Cohen-Or//The Visual Computer. -2008. -P. 24(4). -P. 249-259. - DOI: 10.1007/s00371-007-0197-5
- Koenderink, J.J. Surface shape and curvature scales/J.J. Koenderink, A.J. van Doorn//Image and Vision Computing. -1992. -Vol. 10, Issue 8. -P. 557-564. - DOI: 10.1016/0262-8856(92)90076-F
- Chen, X. A benchmark for 3D mesh segmentation/X. Chen, A. Golovinskiy, T. Funkhouser//ACM Transactions on Graphics. -2009. -Vol. 28, Issue 3. -73. - DOI: 10.1145/1531326.1531379
- Liu, Z. New evaluation metrics for mesh segmentation/Z. Liu, S. Tang, S. Bu, H. Zhang//Computers and Graphics. -2013. -Vol. 37, Issue 6. -P. 553-564. - DOI: 10.1016/j.cag.2013.05.021
- Rafii Zakani, F. New measure for objective evaluation of mesh segmentation algorithms/R. Fafii Zakani, K. Arhid, M. Bouksim, M. Aboulfatah, T. Gadi//2016 4th IEEE International Colloquium on Information Science and Technology (CiSt). -2016. -P. 416-421. - DOI: 10.1109/CIST.2016.7805083
- Rafii Zakani, F. Kulczynski similarity index for objective evaluation of mesh segmentation algorithms/R. Fafii Zakani, K. Arhid, M. Bouksim, T. Gadi, M. Aboulfatah//Proceedings of the 5th International Conference on Multimedia Computing and Systems (ICMCS) 2016. -2016. -P. 12-17. - DOI: 10.1109/ICMCS.2016.7905611
- Arhid, K. An objective 3D mesh segmentation evaluation using Sokal-Sneath metric/K. Arhid, M. Bouksim, F. Rafii Zakani, T. Gadi, M. Aboulfatah//Proceedings of the 5th International Conference on Multimedia Computing and Systems (ICMCS) 2016. -2016. -P. 29-34. - DOI: 10.1109/ICMCS.2016.7905609
- Bouksim, M. New evaluation method for 3D mesh segmentation/M. Bouksim, F. Rafii Zakani, K. Arhid, M. Aboulfatah, T. Gadi//4th IEEE International Colloquium on Information Science and Technology (CiSt) 2016. -2016. -P. 438-443. - DOI: 10.1109/CIST.2016.7805087
- Bouksim, M. Evaluation of 3D mesh segmentation using a weighted version of the Ochiai index/M. Bouksim, F. Rafii Zakani, K. Arhid, T. Gadi, M. Aboulfatah//IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA). -2016. -P. 1-7. - DOI: 10.1109/AICCSA.2016.7945640
- Rafii Zakani, F. A new evaluation method for mesh segmentation based on the Levenshtein distance/F. Rafii Zakani, K. Arhid, M. Bouksim, M. Aboulfatah, T. Gadi//International Review on Computers and Software (IRECOS). -2016. -Vol. 11, Issue 12. -1117. - DOI: 10.15866/irecos.v11i12.10922
- Golovinskiy, A. Randomized cuts for 3D mesh analysis/A. Golovinskiy, T. Funkhouser//ACM Transactions on Graphics. -2008. -Vol. 27, Issue 5. -145. - DOI: 10.1145/1409060.1409098
- Attene, M. Hierarchical mesh segmentation based on fitting primitives/M. Attene, B. Falcidieno, M. Spagnuolo//The Visual Computer. -2006. -Vol. 22, Issue 3. -P. 181-193. - DOI: 10.1007/s00371-006-0375-x
Статья научная
