KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917813625552896 |
|---|---|
| author | Nom, Vannkinh Bakkali, Souhail Luqman, Muhammad Muzzamil Coustaty, Mickaël Ogier, Jean-Marc |
| author_facet | Nom, Vannkinh Bakkali, Souhail Luqman, Muhammad Muzzamil Coustaty, Mickaël Ogier, Jean-Marc |
| contents | Developing effective scene text detection and recognition models hinges on extensive training data, which can be both laborious and costly to obtain, especially for low-resourced languages. Conventional methods tailored for Latin characters often falter with non-Latin scripts due to challenges like character stacking, diacritics, and variable character widths without clear word boundaries. In this paper, we introduce the first Khmer scene-text dataset, featuring 1,544 expert-annotated images, including 997 indoor and 547 outdoor scenes. This diverse dataset includes flat text, raised text, poorly illuminated text, distant and partially obscured text. Annotations provide line-level text and polygonal bounding box coordinates for each scene. The benchmark includes baseline models for scene-text detection and recognition tasks, providing a robust starting point for future research endeavors. The KhmerST dataset is publicly accessible at https://gitlab.com/vannkinhnom123/khmerst. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_18277 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark Nom, Vannkinh Bakkali, Souhail Luqman, Muhammad Muzzamil Coustaty, Mickaël Ogier, Jean-Marc Computer Vision and Pattern Recognition Developing effective scene text detection and recognition models hinges on extensive training data, which can be both laborious and costly to obtain, especially for low-resourced languages. Conventional methods tailored for Latin characters often falter with non-Latin scripts due to challenges like character stacking, diacritics, and variable character widths without clear word boundaries. In this paper, we introduce the first Khmer scene-text dataset, featuring 1,544 expert-annotated images, including 997 indoor and 547 outdoor scenes. This diverse dataset includes flat text, raised text, poorly illuminated text, distant and partially obscured text. Annotations provide line-level text and polygonal bounding box coordinates for each scene. The benchmark includes baseline models for scene-text detection and recognition tasks, providing a robust starting point for future research endeavors. The KhmerST dataset is publicly accessible at https://gitlab.com/vannkinhnom123/khmerst. |
| title | KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.18277 |