Total Disentanglement of Font Images into Style and Character Class Features
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911149374570496 |
|---|---|
| author | Haraguchi, Daichi Shimoda, Wataru Yamaguchi, Kota Uchida, Seiichi |
| author_facet | Haraguchi, Daichi Shimoda, Wataru Yamaguchi, Kota Uchida, Seiichi |
| contents | In this paper, we demonstrate a total disentanglement of font images. Total disentanglement is a neural network-based method for decomposing each font image nonlinearly and completely into its style and content (i.e., character class) features. It uses a simple but careful training procedure to extract the common style feature from all `A'-`Z' images in the same font and the common content feature from all `A' (or another class) images in different fonts. These disentangled features guarantee the reconstruction of the original font image. Various experiments have been conducted to understand the performance of total disentanglement. First, it is demonstrated that total disentanglement is achievable with very high accuracy; this is experimental proof of the long-standing open question, ``Does `A'-ness exist?'' Hofstadter (1985). Second, it is demonstrated that the disentangled features produced by total disentanglement apply to a variety of tasks, including font recognition, character recognition, and one-shot font image generation. Code is available here: https://github.com/uchidalab/total_disentanglement |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12784 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Total Disentanglement of Font Images into Style and Character Class Features Haraguchi, Daichi Shimoda, Wataru Yamaguchi, Kota Uchida, Seiichi Computer Vision and Pattern Recognition In this paper, we demonstrate a total disentanglement of font images. Total disentanglement is a neural network-based method for decomposing each font image nonlinearly and completely into its style and content (i.e., character class) features. It uses a simple but careful training procedure to extract the common style feature from all `A'-`Z' images in the same font and the common content feature from all `A' (or another class) images in different fonts. These disentangled features guarantee the reconstruction of the original font image. Various experiments have been conducted to understand the performance of total disentanglement. First, it is demonstrated that total disentanglement is achievable with very high accuracy; this is experimental proof of the long-standing open question, ``Does `A'-ness exist?'' Hofstadter (1985). Second, it is demonstrated that the disentangled features produced by total disentanglement apply to a variety of tasks, including font recognition, character recognition, and one-shot font image generation. Code is available here: https://github.com/uchidalab/total_disentanglement |
| title | Total Disentanglement of Font Images into Style and Character Class Features |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.12784 |