A Repo For Document AI
Las características principales de deepdoctection/deepdoctection son: PDF Processing Tools.
Las alternativas de código abierto para deepdoctection/deepdoctection incluyen: frooodle/stirling-pdf — Stirling-PDF is a web-based PDF management suite used for editing, merging, splitting, and converting PDF documents.… guaguastandup/zotero-pdf2zh — zotero-pdf2zh is a translation system and Zotero plugin designed to convert academic PDF papers into target languages… applicaai/digital-born-pdf-scanner — Many of PDF files that we have downloaded are digital-born, that is contain easily accessible text layer that PDF… ckorzen/pdf-text-extraction-benchmark — This project is about benchmarking and evaluating existing PDF extraction tools on their semantic abilities to extract… apache/pdfbox — Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file… allenai/pawls — Demo Server | Video Tutorial | Paper.
Stirling-PDF is a web-based PDF management suite used for editing, merging, splitting, and converting PDF documents. It functions as a self-hosted document manager, providing a centralized interface for users to manipulate files on a private server. The system features a workflow automation engine that allows for the creation of processing pipelines to handle large volumes of documents without writing custom code. It also includes an optical character recognition tool to convert scanned PDFs into searchable and editable text. Access is managed through single sign-on integration and OIDC comp
zotero-pdf2zh is a translation system and Zotero plugin designed to convert academic PDF papers into target languages using large language model APIs and machine translation services. It functions as an LLM document translator that integrates directly into Zotero libraries to process research documents. The tool distinguishes itself by generating bilingual PDFs with parallel layouts for side-by-side comparison of original and translated text. It also includes a mobile layout optimizer that crops double-column PDFs and stacks them vertically to improve readability on narrow screens. The syste
Many of PDF files that we have downloaded are digital-born, that is contain easily accessible text layer that PDF viewers use to display text. Some are definitely scanned documents, that do not have any text layer at all, some are searchable OCR-processed scans that contain a lot of hidden text.
This project is about benchmarking and evaluating existing PDF extraction tools on their semantic abilities to extract the body texts from PDF documents, especially from scientific articles. It provides (1) a benchmark generator, (2) a ready-to-use benchmark and (3) an extensive evaluation, with…