Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2507.19092 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913959759577088 |
|---|---|
| author | Machidon, Octavian M. Machidon, Alina L. |
| author_facet | Machidon, Octavian M. Machidon, Alina L. |
| contents | The digitization of historical folkloristic materials presents unique challenges due to diverse text layouts, varying print and handwriting styles, and linguistic variations. This study explores different optical character recognition (OCR) approaches for Slovene folkloristic and historical text digitization, integrating both traditional methods and large language models (LLMs) to improve text transcription accuracy while maintaining linguistic and structural integrity. We compare single-stage OCR techniques with multi-stage pipelines that incorporate machine learning-driven post-processing for text normalization and layout reconstruction. While LLM-enhanced methods show promise in refining recognition outputs and improving readability, they also introduce challenges related to unintended modifications, particularly in the preservation of dialectal expressions and historical structures. Our findings provide insights into selecting optimal digitization strategies for large-scale folklore archives and outline recommendations for developing robust OCR pipelines that balance automation with the need for textual authenticity in digital humanities research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19092 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparing OCR Pipelines for Folkloristic Text Digitization Machidon, Octavian M. Machidon, Alina L. Digital Libraries Multimedia The digitization of historical folkloristic materials presents unique challenges due to diverse text layouts, varying print and handwriting styles, and linguistic variations. This study explores different optical character recognition (OCR) approaches for Slovene folkloristic and historical text digitization, integrating both traditional methods and large language models (LLMs) to improve text transcription accuracy while maintaining linguistic and structural integrity. We compare single-stage OCR techniques with multi-stage pipelines that incorporate machine learning-driven post-processing for text normalization and layout reconstruction. While LLM-enhanced methods show promise in refining recognition outputs and improving readability, they also introduce challenges related to unintended modifications, particularly in the preservation of dialectal expressions and historical structures. Our findings provide insights into selecting optimal digitization strategies for large-scale folklore archives and outline recommendations for developing robust OCR pipelines that balance automation with the need for textual authenticity in digital humanities research. |
| title | Comparing OCR Pipelines for Folkloristic Text Digitization |
| topic | Digital Libraries Multimedia |
| url | https://arxiv.org/abs/2507.19092 |