{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:09:07Z","timestamp":1760609347122,"version":"build-2065373602"},"reference-count":28,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>With the widespread success of deep learning in the two-dimensional field, how to apply deep learning methods from two-dimensional to three-dimensional field has become a current research hotspot. Among them, the polygon mesh structure in the three-dimensional representation as a complex data structure provides an effective shape approximate representation for the three-dimensional object. Although the traditional method can extract the characteristics of the three-dimensional object through the graphical method, it cannot be applied to more complex objects. However, due to the complexity and irregularity of the mesh data, it is difficult to directly apply convolutional neural networks to 3D mesh data processing. Considering this problem, we propose a deep learning method based on a capsule network to effectively classify mesh data. We first design a polynomial convolution template. Through a sliding operation similar to a two-dimensional image convolution window, we directly sample on the grid surface, and use the window sampling surface as the minimum unit of calculation. Because a high-order polynomial can effectively represent a surface, we fit the approximate shape of the surface through the polynomial, use the polynomial parameter as the shape feature of the surface, and add the center point coordinates and normal vector of the surface as the pose feature of the surface. The feature is used as the feature vector of the surface. At the same time, to solve the problem of the introduction of a large number of pooling layers in traditional convolutional neural networks, the capsule network is introduced. For the problem of nonuniform size of the input grid model, the capsule network attitude parameter learning method is improved by sharing the weight of the attitude matrix. The amount of model parameters is reduced, and the training efficiency of the 3D mesh model is further improved. The experiment is compared with the traditional method and the latest two methods on the SHREC15 data set. Compared with the MeshNet and MeshCNN, the average recognition accuracy in the original test set is improved by 3.4% and 2.1%, and the average after fusion of features the accuracy reaches 93.8%. At the same time, under the premise of short training time, this method can also achieve considerable recognition results through experimental verification. The three-dimensional mesh classification method proposed in this paper combines the advantages of graphics and deep learning methods, and effectively improves the classification effect of 3D mesh model.<\/jats:p>","DOI":"10.3390\/a14030099","type":"journal-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T11:13:26Z","timestamp":1616411606000},"page":"99","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["3D Mesh Model Classification with a Capsule Network"],"prefix":"10.3390","volume":"14","author":[{"given":"Yang","family":"Zheng","sequence":"first","affiliation":[{"name":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, China"}]},{"given":"Jieyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, China"},{"name":"Mobile Network Application Technology Key Laboratory of Zhejiang Province, Ningbo 315211, China"}]},{"given":"Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, China"}]},{"given":"Chen","family":"Tang","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, China"}]},{"given":"Shushi","family":"Yu","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,3,22]]},"reference":[{"key":"ref_1","first-page":"2058","article-title":"3D feature learning via convolutional auto-encoder extreme learning machine","volume":"27","author":"Xie","year":"2015","journal-title":"J. Comput. Aided Des. Comput. Graph."},{"unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., and Xiao, J. (2015, January 7\u201312). 3d shapenets: A deep representation for volumetric shapes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","key":"ref_2"},{"doi-asserted-by":"crossref","unstructured":"Maturana, D., and Scherer, S. (October, January 28). Voxnet: A 3d convolutional neu-ral network for real-time object recognition. Proceedings of the Intelligent Robots and Systems (IROS), 2015 IEEE\/RSJ International Conference on, Hamburg, Germany.","key":"ref_3","DOI":"10.1109\/IROS.2015.7353481"},{"unstructured":"Li, Y., Pirk, S., Su, H., Qi, C.R., and Guibas, L.J. (2016, January 5\u201310). FPNN: Field probing neural networks for 3D data. Proceedings of the Advances in Neural Information Processing Systems, Barcelona, Spain.","key":"ref_4"},{"unstructured":"Wang, D.Z., and Posner, I. (2015, January 13\u201317). Voting for voting in online point cloud object detection. Proceedings of the Robotics: Science and Systems, Rome, Italy.","key":"ref_5"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/3072959.3073608","article-title":"O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis","volume":"36","author":"Wang","year":"2017","journal-title":"ACM Trans. Graph."},{"unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21\u201326). Pointnet: Deep learning on point sets for 3D classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","key":"ref_7"},{"unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). Pointnet++: Deep hierarchical. feature learning on point sets in a metric space. Advances in Neural Information Processing Systems. arXiv.","key":"ref_8"},{"key":"ref_9","first-page":"1","article-title":"MeshCNN: A network with an edge","volume":"38","author":"Hanocka","year":"2019","journal-title":"ACM Trans. Graph."},{"doi-asserted-by":"crossref","unstructured":"Feng, Y., You, H., Zhao, X., and Gao, Y. (2019). MeshNet: Mesh. Neural Network for 3D Shape Representation. arXiv.","key":"ref_10","DOI":"10.1609\/aaai.v33i01.33018279"},{"unstructured":"Yang, Y., Liu, S., Pan, H., Liu, Y., and Tong, X. (19, January 14,). PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Online.","key":"ref_11"},{"doi-asserted-by":"crossref","unstructured":"Wang, J., Wen, C., Fu, Y., Lin, H., Zou, T., Xue, X., and Zhang, Y. (2020, January 14\u201319). Neural Pose Transfer by Spatially Adaptive Instance Normalization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","key":"ref_12","DOI":"10.1109\/CVPR42600.2020.00587"},{"unstructured":"Qiao, Y.L., Gao, L., Rosin, P., Lai, Y.K., and Chen, X. (2020). Learning on 3D Meshes with Laplacian Encoding and Pooling. IEEE Trans. Vis. Comput. Graph.","key":"ref_13"},{"doi-asserted-by":"crossref","unstructured":"Litany, O., Bronstein, A., Bronstein, M., and Makadia, A. (2018, January 18\u201322). Deformable shape completion with graph convolutional autoencod-ers. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","key":"ref_14","DOI":"10.1109\/CVPR.2018.00202"},{"doi-asserted-by":"crossref","unstructured":"Zhang, X., Luo, P., Hu, X., Wang, J., and Zhou, J. (2018, January 17\u201319). Research on Classification Performance of Small-Scale Dataset Based on Capsule Network. Proceedings of the 2018 4th International Conference on Robotics and Artificial Intelligence (ICRAI 2018), Guangzhou, China.","key":"ref_15","DOI":"10.1145\/3297097.3297105"},{"unstructured":"Sabour, S., Frosst, N., and Hinton, G.E. (2017, January 4\u20139). Dynamic routing be-tween capsules. Proceedings of the Neural Information Processing Systems (NIPS), Long Beach, CA, USA.","key":"ref_16"},{"doi-asserted-by":"crossref","unstructured":"Hinton, G.E., Krizhevsky, A., and Wang, S.D. (2011, January 14\u201317). Transforming auto-encoders. Proceedings of the International Conference on Artificial Neural Networks (ICANN), Espoo, Finland.","key":"ref_17","DOI":"10.1007\/978-3-642-21735-7_6"},{"unstructured":"Ren, H., Su, J., and Lu, H. (2019). Evaluating Generalization Ability of Convo-lutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification. arXiv.","key":"ref_18"},{"doi-asserted-by":"crossref","unstructured":"Iesmantas, T., and Alzbutas, R. (2018). Convolutional capsule network for classification of breast cancer histology images. International Conference Image Analysis and Recognition (ICIAR), Springer.","key":"ref_19","DOI":"10.1007\/978-3-319-93000-8_97"},{"doi-asserted-by":"crossref","unstructured":"Jaiswal, A., Abdalmageed, W., Wu, Y., and Natarajan, P. (2018, January 8\u201314). Capsulegan: Generative adversarial capsule network. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","key":"ref_20","DOI":"10.1007\/978-3-030-11015-4_38"},{"unstructured":"Yang, M., Zhao, W., Ye, J., Lei, Z., Zhao, Z., and Zhang, S. (November, January 31). Investigating capsule networks with dynamic routing for text classi-fication. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium.","key":"ref_21"},{"doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Yamagishi, J., and Echizen, I. (2019, January 12\u201317). Capsule-forensics: Using capsule networks to detect forged images and videos. Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","key":"ref_22","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"188056","DOI":"10.1109\/ACCESS.2020.3031812","article-title":"DCG-Net: Dynamic Capsule Graph Convolutional Network for Point Clouds","volume":"8","author":"Bazazian","year":"2020","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Bazazian, D., and Par\u00e9s, M. (2021). EDC-Net: Edge Detection Capsule Network for 3D Point Clouds. Appl. Sci., 11.","key":"ref_24","DOI":"10.3390\/app11041833"},{"doi-asserted-by":"crossref","unstructured":"Zhao, Y., Birdal, T., Deng, H., and Tombari, F. (2019, January 15\u201320). 3D point capsule networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","key":"ref_25","DOI":"10.1109\/CVPR.2019.00110"},{"doi-asserted-by":"crossref","unstructured":"Ahmad, A., Kakillioglu, B., and Velipasalar, S. (2018, January 28\u201331). 3D capsule networks for object classification from 3D model data. Proceedings of the 2018 52nd Asilomar Conference on Signals, Systems, and Computers, California, CA, USA.","key":"ref_26","DOI":"10.1109\/ACSSC.2018.8645256"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to doc-ument recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1145\/1015706.1015770","article-title":"Shape matching andanisotropy","volume":"23","author":"Kazhdan","year":"2004","journal-title":"ACM Trans. Graph."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/3\/99\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:39:22Z","timestamp":1760161162000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/3\/99"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,22]]},"references-count":28,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3]]}},"alternative-id":["a14030099"],"URL":"https:\/\/doi.org\/10.3390\/a14030099","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2021,3,22]]}}}