Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913594552090624 |
|---|---|
| author | Waly, Alhossien Tarek, Bassant Feteha, Ali Yehia, Rewan Amr, Gasser Fares, Ahmed |
| author_facet | Waly, Alhossien Tarek, Bassant Feteha, Ali Yehia, Rewan Amr, Gasser Fares, Ahmed |
| contents | The problem of converting images of text into plain text is a widely researched topic in both academia and industry. Arabic handwritten Text Recognation (AHTR) poses additional challenges due to diverse handwriting styles and limited labeled data. In this paper we present a complete OCR pipeline that starts with line segmentation using Differentiable Binarization and Adaptive Scale Fusion techniques to ensure accurate detection of text lines. Following segmentation, a CNN-BiLSTM-CTC architecture is applied to recognize characters. Our system, trained on the Arabic Multi-Fonts Dataset (AMFDS), achieves a Character Recognition Rate (CRR) of 99.20% and a Word Recognition Rate (WRR) of 93.75% on single-word samples containing 7 to 10 characters, along with a CRR of 83.76% for sentences. These results demonstrate the system's strong performance in handling Arabic scripts, establishing a new benchmark for AHTR systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01601 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection Waly, Alhossien Tarek, Bassant Feteha, Ali Yehia, Rewan Amr, Gasser Fares, Ahmed Computer Vision and Pattern Recognition 68T10 The problem of converting images of text into plain text is a widely researched topic in both academia and industry. Arabic handwritten Text Recognation (AHTR) poses additional challenges due to diverse handwriting styles and limited labeled data. In this paper we present a complete OCR pipeline that starts with line segmentation using Differentiable Binarization and Adaptive Scale Fusion techniques to ensure accurate detection of text lines. Following segmentation, a CNN-BiLSTM-CTC architecture is applied to recognize characters. Our system, trained on the Arabic Multi-Fonts Dataset (AMFDS), achieves a Character Recognition Rate (CRR) of 99.20% and a Word Recognition Rate (WRR) of 93.75% on single-word samples containing 7 to 10 characters, along with a CRR of 83.76% for sentences. These results demonstrate the system's strong performance in handling Arabic scripts, establishing a new benchmark for AHTR systems. |
| title | Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection |
| topic | Computer Vision and Pattern Recognition 68T10 |
| url | https://arxiv.org/abs/2412.01601 |