Efficiently Leveraging Linguistic Priors for Scene Text Spotting
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910345333833728 |
|---|---|
| author | Nguyen, Nguyen Tian, Yapeng Xu, Chenliang |
| author_facet | Nguyen, Nguyen Tian, Yapeng Xu, Chenliang |
| contents | Incorporating linguistic knowledge can improve scene text recognition, but it is questionable whether the same holds for scene text spotting, which typically involves text detection and recognition. This paper proposes a method that leverages linguistic knowledge from a large text corpus to replace the traditional one-hot encoding used in auto-regressive scene text spotting and recognition models. This allows the model to capture the relationship between characters in the same word. Additionally, we introduce a technique to generate text distributions that align well with scene text datasets, removing the need for in-domain fine-tuning. As a result, the newly created text distributions are more informative than pure one-hot encoding, leading to improved spotting and recognition performance. Our method is simple and efficient, and it can easily be integrated into existing auto-regressive-based approaches. Experimental results show that our method not only improves recognition accuracy but also enables more accurate localization of words. It significantly improves both state-of-the-art scene text spotting and recognition pipelines, achieving state-of-the-art results on several benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17134 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficiently Leveraging Linguistic Priors for Scene Text Spotting Nguyen, Nguyen Tian, Yapeng Xu, Chenliang Computer Vision and Pattern Recognition Incorporating linguistic knowledge can improve scene text recognition, but it is questionable whether the same holds for scene text spotting, which typically involves text detection and recognition. This paper proposes a method that leverages linguistic knowledge from a large text corpus to replace the traditional one-hot encoding used in auto-regressive scene text spotting and recognition models. This allows the model to capture the relationship between characters in the same word. Additionally, we introduce a technique to generate text distributions that align well with scene text datasets, removing the need for in-domain fine-tuning. As a result, the newly created text distributions are more informative than pure one-hot encoding, leading to improved spotting and recognition performance. Our method is simple and efficient, and it can easily be integrated into existing auto-regressive-based approaches. Experimental results show that our method not only improves recognition accuracy but also enables more accurate localization of words. It significantly improves both state-of-the-art scene text spotting and recognition pipelines, achieving state-of-the-art results on several benchmarks. |
| title | Efficiently Leveraging Linguistic Priors for Scene Text Spotting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.17134 |