Inverse Scene Text Removal
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915359655723008 |
|---|---|
| author | Yoshimatsu, Takumi Takezaki, Shumpei Uchida, Seiichi |
| author_facet | Yoshimatsu, Takumi Takezaki, Shumpei Uchida, Seiichi |
| contents | Scene text removal (STR) aims to erase textual elements from images. It was originally intended for removing privacy-sensitiveor undesired texts from natural scene images, but is now also appliedto typographic images. STR typically detects text regions and theninpaints them. Although STR has advanced through neural networksand synthetic data, misuse risks have increased. This paper investi-gates Inverse STR (ISTR), which analyzes STR-processed images andfocuses on binary classification (detecting whether an image has un-dergone STR) and localizing removed text regions. We demonstrate inexperiments that these tasks are achievable with high accuracies, en-abling detection of potential misuse and improving STR. We also at-tempt to recover the removed text content by training a text recognizerto understand its difficulty. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21002 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Inverse Scene Text Removal Yoshimatsu, Takumi Takezaki, Shumpei Uchida, Seiichi Computer Vision and Pattern Recognition Scene text removal (STR) aims to erase textual elements from images. It was originally intended for removing privacy-sensitiveor undesired texts from natural scene images, but is now also appliedto typographic images. STR typically detects text regions and theninpaints them. Although STR has advanced through neural networksand synthetic data, misuse risks have increased. This paper investi-gates Inverse STR (ISTR), which analyzes STR-processed images andfocuses on binary classification (detecting whether an image has un-dergone STR) and localizing removed text regions. We demonstrate inexperiments that these tasks are achievable with high accuracies, en-abling detection of potential misuse and improving STR. We also at-tempt to recover the removed text content by training a text recognizerto understand its difficulty. |
| title | Inverse Scene Text Removal |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.21002 |