Cascaded Dual-Inpainting Network for Scene Text
Scene text inpainting is a significant research challenge in visual text processing, with critical applications spanning incomplete traffic sign comprehension, degraded container-code recognition, occluded vehicle license plate processing, and other incomplete scene text processing systems. In this...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/14/7742 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839616573974773760 |
|---|---|
| author | Chunmei Liu |
| author_facet | Chunmei Liu |
| author_sort | Chunmei Liu |
| collection | DOAJ |
| description | Scene text inpainting is a significant research challenge in visual text processing, with critical applications spanning incomplete traffic sign comprehension, degraded container-code recognition, occluded vehicle license plate processing, and other incomplete scene text processing systems. In this paper, a cascaded dual-inpainting network for scene text (CDINST) is proposed. The architecture integrates two scene text inpainting models to reconstruct the text foreground: the Structure Generation Module (SGM) and Structure Reconstruction Module (SRM). The SGM primarily performs preliminary foreground text reconstruction and extracts text structures. Building upon the SGM’s guidance, the SRM subsequently enhances the foreground structure reconstruction through structure-guided refinement. The experimental results demonstrate compelling performance on the benchmark dataset, showcasing both the effectiveness of the proposed dual-inpainting network and its accuracy in incomplete scene text recognition. The proposed network achieves an average recognition accuracy improvement of 11.94% compared to baseline methods for incomplete scene text recognition tasks. |
| format | Article |
| id | doaj-art-4be5a3781fdb4c848a77b8082d4c1d79 |
| institution | Matheson Library |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-4be5a3781fdb4c848a77b8082d4c1d792025-07-25T13:12:13ZengMDPI AGApplied Sciences2076-34172025-07-011514774210.3390/app15147742Cascaded Dual-Inpainting Network for Scene TextChunmei Liu0School of Computer Science and Technology, Tongji University, Shanghai 201804, ChinaScene text inpainting is a significant research challenge in visual text processing, with critical applications spanning incomplete traffic sign comprehension, degraded container-code recognition, occluded vehicle license plate processing, and other incomplete scene text processing systems. In this paper, a cascaded dual-inpainting network for scene text (CDINST) is proposed. The architecture integrates two scene text inpainting models to reconstruct the text foreground: the Structure Generation Module (SGM) and Structure Reconstruction Module (SRM). The SGM primarily performs preliminary foreground text reconstruction and extracts text structures. Building upon the SGM’s guidance, the SRM subsequently enhances the foreground structure reconstruction through structure-guided refinement. The experimental results demonstrate compelling performance on the benchmark dataset, showcasing both the effectiveness of the proposed dual-inpainting network and its accuracy in incomplete scene text recognition. The proposed network achieves an average recognition accuracy improvement of 11.94% compared to baseline methods for incomplete scene text recognition tasks.https://www.mdpi.com/2076-3417/15/14/7742scene text processingincomplete scene textscene text inpaintingscene text structure extractionincomplete scene text recognition |
| spellingShingle | Chunmei Liu Cascaded Dual-Inpainting Network for Scene Text Applied Sciences scene text processing incomplete scene text scene text inpainting scene text structure extraction incomplete scene text recognition |
| title | Cascaded Dual-Inpainting Network for Scene Text |
| title_full | Cascaded Dual-Inpainting Network for Scene Text |
| title_fullStr | Cascaded Dual-Inpainting Network for Scene Text |
| title_full_unstemmed | Cascaded Dual-Inpainting Network for Scene Text |
| title_short | Cascaded Dual-Inpainting Network for Scene Text |
| title_sort | cascaded dual inpainting network for scene text |
| topic | scene text processing incomplete scene text scene text inpainting scene text structure extraction incomplete scene text recognition |
| url | https://www.mdpi.com/2076-3417/15/14/7742 |
| work_keys_str_mv | AT chunmeiliu cascadeddualinpaintingnetworkforscenetext |