3D Mesh Model Classification with a Capsule Network
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 struct...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/14/3/99 |
| _version_ | 1797540400406200320 |
|---|---|
| author | Yang Zheng Jieyu Zhao Yu Chen Chen Tang Shushi Yu |
| author_facet | Yang Zheng Jieyu Zhao Yu Chen Chen Tang Shushi Yu |
| author_sort | Yang Zheng |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T12:59:37Z |
| format | Article |
| id | doaj.art-0582ecf4bf95449c95a368e60b38f5a2 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-10T12:59:37Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-0582ecf4bf95449c95a368e60b38f5a22023-11-21T11:33:28ZengMDPI AGAlgorithms1999-48932021-03-011439910.3390/a140300993D Mesh Model Classification with a Capsule NetworkYang Zheng0Jieyu Zhao1Yu Chen2Chen Tang3Shushi Yu4Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaWith 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.https://www.mdpi.com/1999-4893/14/3/99capsule networkpoolingthree-dimensional recognitionfeature extraction |
| spellingShingle | Yang Zheng Jieyu Zhao Yu Chen Chen Tang Shushi Yu 3D Mesh Model Classification with a Capsule Network Algorithms capsule network pooling three-dimensional recognition feature extraction |
| title | 3D Mesh Model Classification with a Capsule Network |
| title_full | 3D Mesh Model Classification with a Capsule Network |
| title_fullStr | 3D Mesh Model Classification with a Capsule Network |
| title_full_unstemmed | 3D Mesh Model Classification with a Capsule Network |
| title_short | 3D Mesh Model Classification with a Capsule Network |
| title_sort | 3d mesh model classification with a capsule network |
| topic | capsule network pooling three-dimensional recognition feature extraction |
| url | https://www.mdpi.com/1999-4893/14/3/99 |
| work_keys_str_mv | AT yangzheng 3dmeshmodelclassificationwithacapsulenetwork AT jieyuzhao 3dmeshmodelclassificationwithacapsulenetwork AT yuchen 3dmeshmodelclassificationwithacapsulenetwork AT chentang 3dmeshmodelclassificationwithacapsulenetwork AT shushiyu 3dmeshmodelclassificationwithacapsulenetwork |