Nonlinear optimization generating the Tomb Mural Blocks by GANS
Tomb murals are the special kind of murals that are buried underground. Due to the narrow exit of the tomb passage, the tomb murals were excavated by dividing the whole mural into blocks, which made lots of information missing between the blocks. The digital restoration technology Image inpainting u...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2020-12-01
|
| Series: | Applied Mathematics and Nonlinear Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/amns.2020.2.00072 |
| _version_ | 1818307477118124032 |
|---|---|
| author | Wu Meng Payshanbiev Adim Zhao Qing Yang Wenzong |
| author_facet | Wu Meng Payshanbiev Adim Zhao Qing Yang Wenzong |
| author_sort | Wu Meng |
| collection | DOAJ |
| description | Tomb murals are the special kind of murals that are buried underground. Due to the narrow exit of the tomb passage, the tomb murals were excavated by dividing the whole mural into blocks, which made lots of information missing between the blocks. The digital restoration technology Image inpainting uses the edge information around the missing parts to spread the information inside of the defect area and fills the information from the outside to the inside. But it is not suitable for filling the missing parts between the tomb mural blocks. Because these parts are large for exemplar-based inpainting which may make texture dislocation and for PDE which may make cartoon blur. It is a need to generate the information outwards to complete the information. The generative adversarial network uses deep learning training by the murals remains to generate the information from inside to outside, but the typical GAN doesn‘t have a good nonlinear feature. This paper provided a generating technology based on the deep convolution generative adversarial network to rebuild the missing information between the tomb mural blocks. It built the training data set of the simulation platform with Keras and designed a whole mural generation scheme based on DCGAN. In order to get better generated results to avoid the bad artifacts; it adds the nonlinear layers by choosing 13 layers convolution and 2 deconvolution layers of the generator and contained 5 layers convolution discriminator; it designed a new phased nonlinear loss function by using Pycharm pretreatment for Numpy array file data sets; finally, it completed the generate tomb mural information to obtain the good simulation effect. |
| first_indexed | 2024-12-13T06:59:00Z |
| format | Article |
| id | doaj.art-4eb1d20863084c75a89624702847501c |
| institution | Directory Open Access Journal |
| issn | 2444-8656 |
| language | English |
| last_indexed | 2024-12-13T06:59:00Z |
| publishDate | 2020-12-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Mathematics and Nonlinear Sciences |
| spelling | doaj.art-4eb1d20863084c75a89624702847501c2022-12-21T23:55:59ZengSciendoApplied Mathematics and Nonlinear Sciences2444-86562020-12-0161435610.2478/amns.2020.2.00072Nonlinear optimization generating the Tomb Mural Blocks by GANSWu Meng0Payshanbiev Adim1Zhao Qing2Yang Wenzong3School of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an710055, ChinaSchool of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an710055, ChinaSchool of Literature, Language and Law, Xi’an University of Architecture and Technology, Xi’an710055, ChinaShaanxi History Museum, Xi’an710061, Shaanxi, ChinaTomb murals are the special kind of murals that are buried underground. Due to the narrow exit of the tomb passage, the tomb murals were excavated by dividing the whole mural into blocks, which made lots of information missing between the blocks. The digital restoration technology Image inpainting uses the edge information around the missing parts to spread the information inside of the defect area and fills the information from the outside to the inside. But it is not suitable for filling the missing parts between the tomb mural blocks. Because these parts are large for exemplar-based inpainting which may make texture dislocation and for PDE which may make cartoon blur. It is a need to generate the information outwards to complete the information. The generative adversarial network uses deep learning training by the murals remains to generate the information from inside to outside, but the typical GAN doesn‘t have a good nonlinear feature. This paper provided a generating technology based on the deep convolution generative adversarial network to rebuild the missing information between the tomb mural blocks. It built the training data set of the simulation platform with Keras and designed a whole mural generation scheme based on DCGAN. In order to get better generated results to avoid the bad artifacts; it adds the nonlinear layers by choosing 13 layers convolution and 2 deconvolution layers of the generator and contained 5 layers convolution discriminator; it designed a new phased nonlinear loss function by using Pycharm pretreatment for Numpy array file data sets; finally, it completed the generate tomb mural information to obtain the good simulation effect.https://doi.org/10.2478/amns.2020.2.00072nonlinear optimizationtomb muralgenerative adversarial networkloss function65j1547j0694a0890c35 |
| spellingShingle | Wu Meng Payshanbiev Adim Zhao Qing Yang Wenzong Nonlinear optimization generating the Tomb Mural Blocks by GANS Applied Mathematics and Nonlinear Sciences nonlinear optimization tomb mural generative adversarial network loss function 65j15 47j06 94a08 90c35 |
| title | Nonlinear optimization generating the Tomb Mural Blocks by GANS |
| title_full | Nonlinear optimization generating the Tomb Mural Blocks by GANS |
| title_fullStr | Nonlinear optimization generating the Tomb Mural Blocks by GANS |
| title_full_unstemmed | Nonlinear optimization generating the Tomb Mural Blocks by GANS |
| title_short | Nonlinear optimization generating the Tomb Mural Blocks by GANS |
| title_sort | nonlinear optimization generating the tomb mural blocks by gans |
| topic | nonlinear optimization tomb mural generative adversarial network loss function 65j15 47j06 94a08 90c35 |
| url | https://doi.org/10.2478/amns.2020.2.00072 |
| work_keys_str_mv | AT wumeng nonlinearoptimizationgeneratingthetombmuralblocksbygans AT payshanbievadim nonlinearoptimizationgeneratingthetombmuralblocksbygans AT zhaoqing nonlinearoptimizationgeneratingthetombmuralblocksbygans AT yangwenzong nonlinearoptimizationgeneratingthetombmuralblocksbygans |