Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.04223 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909480673869824 |
|---|---|
| author | Karmanov, Ilia Deshmukh, Amala Sanjay Voegtle, Lukas Fischer, Philipp Chumachenko, Kateryna Roman, Timo Seppänen, Jarno Parmar, Jupinder Jennings, Joseph Tao, Andrew Sapra, Karan |
| author_facet | Karmanov, Ilia Deshmukh, Amala Sanjay Voegtle, Lukas Fischer, Philipp Chumachenko, Kateryna Roman, Timo Seppänen, Jarno Parmar, Jupinder Jennings, Joseph Tao, Andrew Sapra, Karan |
| contents | Optical Character Recognition (OCR) technology is widely used to extract text from images of documents, facilitating efficient digitization and data retrieval. However, merely extracting text is insufficient when dealing with complex documents. Fully comprehending such documents requires an understanding of their structure -- including formatting, formulas, tables, and the reading order of multiple blocks and columns across multiple pages -- as well as semantic information for detecting elements like footnotes and image captions. This comprehensive understanding is crucial for downstream tasks such as retrieval, document question answering, and data curation for training Large Language Models (LLMs) and Vision Language Models (VLMs). To address this, we introduce Éclair, a general-purpose text-extraction tool specifically designed to process a wide range of document types. Given an image, Éclair is able to extract formatted text in reading order, along with bounding boxes and their corresponding semantic classes. To thoroughly evaluate these novel capabilities, we introduce our diverse human-annotated benchmark for document-level OCR and semantic classification. Éclair achieves state-of-the-art accuracy on this benchmark, outperforming other methods across key metrics. Additionally, we evaluate Éclair on established benchmarks, demonstrating its versatility and strength across several evaluation standards. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04223 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Éclair -- Extracting Content and Layout with Integrated Reading Order for Documents Karmanov, Ilia Deshmukh, Amala Sanjay Voegtle, Lukas Fischer, Philipp Chumachenko, Kateryna Roman, Timo Seppänen, Jarno Parmar, Jupinder Jennings, Joseph Tao, Andrew Sapra, Karan Computer Vision and Pattern Recognition Optical Character Recognition (OCR) technology is widely used to extract text from images of documents, facilitating efficient digitization and data retrieval. However, merely extracting text is insufficient when dealing with complex documents. Fully comprehending such documents requires an understanding of their structure -- including formatting, formulas, tables, and the reading order of multiple blocks and columns across multiple pages -- as well as semantic information for detecting elements like footnotes and image captions. This comprehensive understanding is crucial for downstream tasks such as retrieval, document question answering, and data curation for training Large Language Models (LLMs) and Vision Language Models (VLMs). To address this, we introduce Éclair, a general-purpose text-extraction tool specifically designed to process a wide range of document types. Given an image, Éclair is able to extract formatted text in reading order, along with bounding boxes and their corresponding semantic classes. To thoroughly evaluate these novel capabilities, we introduce our diverse human-annotated benchmark for document-level OCR and semantic classification. Éclair achieves state-of-the-art accuracy on this benchmark, outperforming other methods across key metrics. Additionally, we evaluate Éclair on established benchmarks, demonstrating its versatility and strength across several evaluation standards. |
| title | Éclair -- Extracting Content and Layout with Integrated Reading Order for Documents |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.04223 |