Shape Modeling Based on Convolutional Restricted Boltzmann Machines
This paper proposes a kind of shape model based on convolutional restricted Boltzmann machines(CRBM), which can be used to assist the task of image target detection and classification. The CRBM is a generative model that can model shapes through the generative capabilities of the model. This paper p...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2018-01-01
|
| Series: | MATEC Web of Conferences |
| Online Access: | https://doi.org/10.1051/matecconf/201817301022 |
| _version_ | 1819169798564610048 |
|---|---|
| author | Wang Xi-Li Chen Fen |
| author_facet | Wang Xi-Li Chen Fen |
| author_sort | Wang Xi-Li |
| collection | DOAJ |
| description | This paper proposes a kind of shape model based on convolutional restricted Boltzmann machines(CRBM), which can be used to assist the task of image target detection and classification. The CRBM is a generative model that can model shapes through the generative capabilities of the model. This paper presents the visual representation, construction process and training method of the model construction. This paper does experiments on the Weizmann Horse dataset. The results show that, compared with RBM, although the training time of this model is slightly longer, the test time of the model is similar, and it can better shape modeling, modeling of the details of the shape can be well expressed. The samples generated from CRBM look more realistic. The difference between the shape and the original shape generated by Euclidean distance measurement shows that the model has a strong ability to model shapes. |
| first_indexed | 2024-12-22T19:25:14Z |
| format | Article |
| id | doaj.art-7214218770494ea9b177a737c4eb0e8b |
| institution | Directory Open Access Journal |
| issn | 2261-236X |
| language | English |
| last_indexed | 2024-12-22T19:25:14Z |
| publishDate | 2018-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | MATEC Web of Conferences |
| spelling | doaj.art-7214218770494ea9b177a737c4eb0e8b2022-12-21T18:15:15ZengEDP SciencesMATEC Web of Conferences2261-236X2018-01-011730102210.1051/matecconf/201817301022matecconf_smima2018_01022Shape Modeling Based on Convolutional Restricted Boltzmann MachinesWang Xi-LiChen FenThis paper proposes a kind of shape model based on convolutional restricted Boltzmann machines(CRBM), which can be used to assist the task of image target detection and classification. The CRBM is a generative model that can model shapes through the generative capabilities of the model. This paper presents the visual representation, construction process and training method of the model construction. This paper does experiments on the Weizmann Horse dataset. The results show that, compared with RBM, although the training time of this model is slightly longer, the test time of the model is similar, and it can better shape modeling, modeling of the details of the shape can be well expressed. The samples generated from CRBM look more realistic. The difference between the shape and the original shape generated by Euclidean distance measurement shows that the model has a strong ability to model shapes.https://doi.org/10.1051/matecconf/201817301022 |
| spellingShingle | Wang Xi-Li Chen Fen Shape Modeling Based on Convolutional Restricted Boltzmann Machines MATEC Web of Conferences |
| title | Shape Modeling Based on Convolutional Restricted Boltzmann Machines |
| title_full | Shape Modeling Based on Convolutional Restricted Boltzmann Machines |
| title_fullStr | Shape Modeling Based on Convolutional Restricted Boltzmann Machines |
| title_full_unstemmed | Shape Modeling Based on Convolutional Restricted Boltzmann Machines |
| title_short | Shape Modeling Based on Convolutional Restricted Boltzmann Machines |
| title_sort | shape modeling based on convolutional restricted boltzmann machines |
| url | https://doi.org/10.1051/matecconf/201817301022 |
| work_keys_str_mv | AT wangxili shapemodelingbasedonconvolutionalrestrictedboltzmannmachines AT chenfen shapemodelingbasedonconvolutionalrestrictedboltzmannmachines |