LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913535268749312 |
|---|---|
| author | Pilligua, Maria Biescas, Nil Vazquez-Corral, Javier Lladós, Josep Valveny, Ernest Biswas, Sanket |
| author_facet | Pilligua, Maria Biescas, Nil Vazquez-Corral, Javier Lladós, Josep Valveny, Ernest Biswas, Sanket |
| contents | The rapid evolution of intelligent document processing systems demands robust solutions that adapt to diverse domains without extensive retraining. Traditional methods often falter with variable document types, leading to poor performance. To overcome these limitations, this paper introduces a text-graphic layer separation approach that enhances domain adaptability in document image restoration (DIR) systems. We propose LayeredDoc, which utilizes two layers of information: the first targets coarse-grained graphic components, while the second refines machine-printed textual content. This hierarchical DIR framework dynamically adjusts to the characteristics of the input document, facilitating effective domain adaptation. We evaluated our approach both qualitatively and quantitatively using a new real-world dataset, LayeredDocDB, developed for this study. Initially trained on a synthetically generated dataset, our model demonstrates strong generalization capabilities for the DIR task, offering a promising solution for handling variability in real-world data. Our code is accessible on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08610 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach Pilligua, Maria Biescas, Nil Vazquez-Corral, Javier Lladós, Josep Valveny, Ernest Biswas, Sanket Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning The rapid evolution of intelligent document processing systems demands robust solutions that adapt to diverse domains without extensive retraining. Traditional methods often falter with variable document types, leading to poor performance. To overcome these limitations, this paper introduces a text-graphic layer separation approach that enhances domain adaptability in document image restoration (DIR) systems. We propose LayeredDoc, which utilizes two layers of information: the first targets coarse-grained graphic components, while the second refines machine-printed textual content. This hierarchical DIR framework dynamically adjusts to the characteristics of the input document, facilitating effective domain adaptation. We evaluated our approach both qualitatively and quantitatively using a new real-world dataset, LayeredDocDB, developed for this study. Initially trained on a synthetically generated dataset, our model demonstrates strong generalization capabilities for the DIR task, offering a promising solution for handling variability in real-world data. Our code is accessible on GitHub. |
| title | LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.08610 |