Deep learning model-based brand design 3D image construction
In order to have a better product display and thus attract consumers’ purchases and increase the economic benefits of the enterprise, in this paper, we propose a deep learning model for brand 3D image design. A feedforward neural network that estimates the error of previous layers based on the error...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2024-01-01
|
| Series: | Applied Mathematics and Nonlinear Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/amns.2023.1.00117 |
| _version_ | 1797340891723071488 |
|---|---|
| author | Huang Zeping Chen Mengtian |
| author_facet | Huang Zeping Chen Mengtian |
| author_sort | Huang Zeping |
| collection | DOAJ |
| description | In order to have a better product display and thus attract consumers’ purchases and increase the economic benefits of the enterprise, in this paper, we propose a deep learning model for brand 3D image design. A feedforward neural network that estimates the error of previous layers based on the error of the output layer assigns the convolutional kernel weight parameters of the network in the interval and stops when the error reaches a preset accuracy or reaches a preset maximum learning count. The locally-aware convolutional neural network acquires local features that are finer than the global features and outputs the feature maps of the convolutional layers after passing the activation function to calculate the sensitivity of the sampled layer units. Given the sensitivity information of the feature map, the gradient of the kernel function weights is obtained, and the updated parameters are trained to achieve feature map recursion and solve the image boundary problem. A 3D recurrent neural network is constructed using data-driven multiple or single images, transformed into a low-dimensional feature matrix, processed with 3D pixel data, extracted perceptual features, and generated high-resolution images. The analysis of the results shows that the CD value of the used model is 0.477 and the EMD value is 0.579, which makes the constructed 3D images with more obvious detail levels and more accurate structural design, while the model of Pixel2Mesh focuses more on surface information, so the generated model is more realistic and closer to the real image. |
| first_indexed | 2024-03-08T10:11:00Z |
| format | Article |
| id | doaj.art-97d88a0ff9aa4e6882381d6f3ef7e825 |
| institution | Directory Open Access Journal |
| issn | 2444-8656 |
| language | English |
| last_indexed | 2024-03-08T10:11:00Z |
| publishDate | 2024-01-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Mathematics and Nonlinear Sciences |
| spelling | doaj.art-97d88a0ff9aa4e6882381d6f3ef7e8252024-01-29T08:52:25ZengSciendoApplied Mathematics and Nonlinear Sciences2444-86562024-01-019110.2478/amns.2023.1.00117Deep learning model-based brand design 3D image constructionHuang Zeping0Chen Mengtian11School of planning and design, Xinyang Agriculture and Forestry University, Xinyang, 464000, China2Marxism College, Xinyang Agriculture and Forestry University, Xinyang, 464000, ChinaIn order to have a better product display and thus attract consumers’ purchases and increase the economic benefits of the enterprise, in this paper, we propose a deep learning model for brand 3D image design. A feedforward neural network that estimates the error of previous layers based on the error of the output layer assigns the convolutional kernel weight parameters of the network in the interval and stops when the error reaches a preset accuracy or reaches a preset maximum learning count. The locally-aware convolutional neural network acquires local features that are finer than the global features and outputs the feature maps of the convolutional layers after passing the activation function to calculate the sensitivity of the sampled layer units. Given the sensitivity information of the feature map, the gradient of the kernel function weights is obtained, and the updated parameters are trained to achieve feature map recursion and solve the image boundary problem. A 3D recurrent neural network is constructed using data-driven multiple or single images, transformed into a low-dimensional feature matrix, processed with 3D pixel data, extracted perceptual features, and generated high-resolution images. The analysis of the results shows that the CD value of the used model is 0.477 and the EMD value is 0.579, which makes the constructed 3D images with more obvious detail levels and more accurate structural design, while the model of Pixel2Mesh focuses more on surface information, so the generated model is more realistic and closer to the real image.https://doi.org/10.2478/amns.2023.1.00117brand designdeep learning modelconvolutional neural networkimage constructionimage boundary68t05 |
| spellingShingle | Huang Zeping Chen Mengtian Deep learning model-based brand design 3D image construction Applied Mathematics and Nonlinear Sciences brand design deep learning model convolutional neural network image construction image boundary 68t05 |
| title | Deep learning model-based brand design 3D image construction |
| title_full | Deep learning model-based brand design 3D image construction |
| title_fullStr | Deep learning model-based brand design 3D image construction |
| title_full_unstemmed | Deep learning model-based brand design 3D image construction |
| title_short | Deep learning model-based brand design 3D image construction |
| title_sort | deep learning model based brand design 3d image construction |
| topic | brand design deep learning model convolutional neural network image construction image boundary 68t05 |
| url | https://doi.org/10.2478/amns.2023.1.00117 |
| work_keys_str_mv | AT huangzeping deeplearningmodelbasedbranddesign3dimageconstruction AT chenmengtian deeplearningmodelbasedbranddesign3dimageconstruction |