OCR Awesome
约 2 分钟阅读
标签：资源精选
- qwen2.5 vl
- All in One OCR/OCR Toolkit
- PaddleOCR笔记PaddleOCRPaddlePaddle/PaddleOCR · 支持 英文(ch)、英文(en)、法语(french)、德语(german)、韩语(korean)、日语(japan) · ocrversion: PP-OCRv5, PP-OCRv4, PP-OCRv3打开：/notes/ai/ml/paddle/ocr
- Paddle
- by 百度
- paddlejs.baidu.com/ocr链接paddlejs.baidu.com/ocrqwen2.5 vl · All in One OCR/OCR Toolkit · PaddleOCR · Paddle · by 百度 · https://paddlejs.baidu.com/ocr · PaddlePaddle/PaddleOCR笔记：OCR Awesome
- PaddlePaddle/PaddleOCRGitHubPaddlePaddle/PaddleOCRPaddlePaddle/PaddleOCR · 支持 英文(ch)、英文(en)、法语(french)、德语(german)、韩语(korean)、日语(japan) · ocrversion: PP-OCRv5, PP-OCRv4, PP-OCRv3笔记：PaddleOCR
- PaddlePaddle/Paddle.jsGitHubPaddlePaddle/Paddle.js
- 很久没维护了
- hiroi-sora/PaddleOCR-jsonGitHubhiroi-sora/PaddleOCR-json
- 离线，Windows，命令行输出 JSON 结果
- Evezerest/PPOCRLabelGitHubEvezerest/PPOCRLabel
- 半自动化图形标注工具
- PP-OCRv4GitHub 文件PaddlePaddle/PaddleOCR/2.7/doc/doc_ch/PP-OCRv4_introduction.md
- breezedeus/Pix2TextGitHubbreezedeus/Pix2Textbreezedeus/Pix2Text · MIT · 国内开发者维护 · 简体中文&英文 使用的 CnOCR, 其他使用的 EasyOCR · p2t 命令行 https://pix2text.readthedocs.io/zh-cn/stable/command/笔记：Pix2Text
- MIT
- 国内开发者维护
- 简体中文&英文 使用的 CnOCR, 其他使用的 EasyOCR
- p2t 命令行 pix2text.readthedocs.io/zh-cn/stable/command
- macOS 桌面工具 breezedeus/Pix2Text-MacGitHubbreezedeus/Pix2Text-Macbreezedeus/Pix2Text · MIT · 国内开发者维护 · 简体中文&英文 使用的 CnOCR, 其他使用的 EasyOCR · p2t 命令行 https://pix2text.readthedocs.io/zh-cn/stable/command/笔记：Pix2Text
- RapidAI/RapidOCRGitHubRapidAI/RapidOCRRapidAI/RapidOCR · 将 Paddle 处理为 ONNX · 提供更便捷的使用方式，专注于推理部署 · ONNXRuntime、OpenVINO、PaddlePaddle · RapidAI/RapidDoc · RapidAI/RapidTable笔记：RapidOCR
- Apache-2.0, Python
- based on ONNXRuntime, OpenVION, PaddlePaddle
- PaddleOCR -> ONNXRuntime
- OCR, Layout, Table, Form, Receipt, Invoice
- VikParuchuri/suryaGitHubVikParuchuri/suryaVikParuchuri/surya · GPLv3, Python · document OCR · 参考 · https://huggingface.co/spaces/artificialguybr/Surya-OCR · https://github.com/VikParuchuri/surya/blob/master/surya/langua...笔记：surya
- GPLv3, Python
- 支持 Detection, OCR, Layout, Reading Order, Table Recognition
- PaddleOCR笔记PaddleOCRPaddlePaddle/PaddleOCR · 支持 英文(ch)、英文(en)、法语(french)、德语(german)、韩语(korean)、日语(japan) · ocrversion: PP-OCRv5, PP-OCRv4, PP-OCRv3打开：/notes/ai/ml/paddle/ocr
- 基础 OCR/通用 OCR
- EasyOCR
- tesseract
- naptha/tesseract.jsGitHubnaptha/tesseract.js
- Apache-2.0, JS
- naptha/tesseract.jsGitHubnaptha/tesseract.js
- breezedeus/cnocrGitHubbreezedeus/cnocr
- Apache-2.0
- 基于 RapidOCR 集成 PPOCRv4 最新版 OCR 模型
- jingsongliujing/OnnxOCRGitHubjingsongliujing/OnnxOCR
- 基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR
- 表格/Table/Layout/文档
- RapidAI/TableStructureRecGitHubRapidAI/TableStructureRec
- 表格识别算法的集合库
- wired_table_rec 有线表格识别算法
- lineless_table_rec 无线表格识别算法
- RapidAI/RapidTableGitHubRapidAI/RapidTable
- Apache-2.0, Python, ONNX
- 源自 PP-Structure 的表格识别算法，模型转换为ONNX，推理引擎采用ONNXRuntime
- opendatalab/DocLayout-YOLOGitHubopendatalab/DocLayout-YOLOopendatalab/DocLayout-YOLO · AGPLv3, Python, YOLOv10 · https://huggingface.co/spaces/opendatalab/DocLayout-YOLO · classes笔记：DocLayout-YOLO
- AGPLv3, Python, YOLOv10
- HF Space:opendatalab/DocLayout-YOLOHuggingFaceHF Space:opendatalab/DocLayout-YOLOopendatalab/DocLayout-YOLO · AGPLv3, Python, YOLOv10 · https://huggingface.co/spaces/opendatalab/DocLayout-YOLO · classeshuggingface.co · huggingface.co/spaces/opendatalab/DocLayout-YOLO笔记：DocLayout-YOLO
- AlibabaResearch/AdvancedLiterateMachineryGitHubAlibabaResearch/AdvancedLiterateMachinery
- Apache-2.0, Python, C++
- by 阿里巴巴
- RapidAI/TableStructureRecGitHubRapidAI/TableStructureRec
- PDF
- ocrmypdf/OCRmyPDFGitHubocrmypdf/OCRmyPDFocrmypdf/OCRmyPDF · MPL-2.0, Python · adds an OCR text layer to scanned PDF · 流程 · 光栅化 · 预处理 · deskew · clean · 准备图像 · OCR 识别笔记：OCRmyPDF
- MPL-2.0, Python
- adds an OCR text layer to scanned PDF
- paperless-ngx 使用 ocrmypdf
- paperless-ngx
- Stirling-Tools/Stirling-PDFGitHubStirling-Tools/Stirling-PDF
- Apache-2.0, Python, PyTorch
- PDF to Image, OCR, Text Extraction
- 替代掉了了 OCRMyPDF
- ocrmypdf/OCRmyPDFGitHubocrmypdf/OCRmyPDFocrmypdf/OCRmyPDF · MPL-2.0, Python · adds an OCR text layer to scanned PDF · 流程 · 光栅化 · 预处理 · deskew · clean · 准备图像 · OCR 识别笔记：OCRmyPDF
- Formula
- OleehyO/TexTellerGitHubOleehyO/TexTeller
- 使用 PaddleOCR, ONNX
- image to latex formulas
- OleehyO/TexTellerGitHubOleehyO/TexTeller
- Index/Arena
- getomni-ai/zeroxGitHubgetomni-ai/zerox
- MIT
- PDF to Markdown
- 使用 OpenAI, Anthropic, AWS Bedrock
- katanaml/sparrowGitHubkatanaml/sparrow
- GPLv3, Python
- Data processing with ML, LLM and Vision LLM
- mindee/doctrGitHubmindee/doctr
- Apache-2.0, Python, TensorFlow 2, PyTorch
- Walleclipse/ChineseAddress_OCRGitHubWalleclipse/ChineseAddress_OCR
- ooooverflow/chinese-ocrGitHubooooverflow/chinese-ocr
- CRNN
- macOS OCR Live Text
- 直接 Preview 在图片上识别文字
- dynobo/normcapGitHubdynobo/normcap
- OCR powered screen-capture tool
- faustomorales/keras-ocrGitHubfaustomorales/keras-ocr
- TDiblik/main-gate-alprGitHubTDiblik/main-gate-alpr
- license plates
- HN #37384327Hacker NewsHacker News #37384327Hacker News
- kba/awesome-ocrGitHubkba/awesome-ocr
- deepdoctection/deepdoctectionGitHubdeepdoctection/deepdoctection
- Apache-2.0, Python
- 用到了很多东西，可以作为参考
- LayoutLM
- HF:docs/transformersHuggingFaceHF:docs/transformershuggingface.co · huggingface.co/docs/transformers/en/model_doc/layoutlm
- medium.com/@shivarama/layoutlmv3-from-zero-to-hero-part-1-85d05818eec4
- DiT - Document Image Text
- microsoft/unilmGitHubmicrosoft/unilm
- MIT, Python
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
- Unified Language Model Pre-training
- 商业
- Mistral OCR
- doc2x.noedgeai.com
关联信息
反向链接、本文链接的其他页面和外部资料。
反向链接
- OCR笔记 · Awesome
| abbr. | stand for | meaning | · | OCR | Optical Character Recognition | 光学字符识别 | · | MFD | Mathematical Formula Detection | 数学公式检测 |
站内链接
- PaddleOCR笔记 · PaddleOCR
PaddlePaddle/PaddleOCR · 支持 英文(ch)、英文(en)、法语(french)、德语(german)、韩语(korean)、日语(japan) · ocrversion: PP-OCRv5, PP-OCRv4, PP-OCRv3
参考资料
GitHub31 条
- AlibabaResearch/AdvancedLiterateMachinerygithub.com/AlibabaResearch/AdvancedLiterateMachinery
- breezedeus/cnocrgithub.com/breezedeus/cnocr
- breezedeus/Pix2Textgithub.com/breezedeus/Pix2Text
- breezedeus/Pix2Text-Macgithub.com/breezedeus/Pix2Text-Mac
- deepdoctection/deepdoctectiongithub.com/deepdoctection/deepdoctection
- dynobo/normcapgithub.com/dynobo/normcap
- Evezerest/PPOCRLabelgithub.com/Evezerest/PPOCRLabel
- faustomorales/keras-ocrgithub.com/faustomorales/keras-ocr
- getomni-ai/zeroxgithub.com/getomni-ai/zerox
- hiroi-sora/PaddleOCR-jsongithub.com/hiroi-sora/PaddleOCR-json
- jingsongliujing/OnnxOCRgithub.com/jingsongliujing/OnnxOCR
- katanaml/sparrowgithub.com/katanaml/sparrow
- kba/awesome-ocrgithub.com/kba/awesome-ocr
- microsoft/unilmgithub.com/microsoft/unilm
- microsoft/unilm/ditgithub.com/microsoft/unilm/tree/master/dit
- mindee/doctrgithub.com/mindee/doctr
- naptha/tesseract.jsgithub.com/naptha/tesseract.js
- ocrmypdf/OCRmyPDFgithub.com/ocrmypdf/OCRmyPDF
- OleehyO/TexTellergithub.com/OleehyO/TexTeller
- ooooverflow/chinese-ocrgithub.com/ooooverflow/chinese-ocr
- opendatalab/DocLayout-YOLOgithub.com/opendatalab/DocLayout-YOLO
- PaddlePaddle/Paddle.jsgithub.com/PaddlePaddle/Paddle.js
- PaddlePaddle/PaddleOCRgithub.com/PaddlePaddle/PaddleOCR
- PaddlePaddle/PaddleOCR/2.7/doc/doc_ch/PP-OCRv4_introduction.mdgithub.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/PP-OCRv4_introduction.md
- RapidAI/RapidOCRgithub.com/RapidAI/RapidOCR
- RapidAI/RapidTablegithub.com/RapidAI/RapidTable
- RapidAI/TableStructureRecgithub.com/RapidAI/TableStructureRec
- Stirling-Tools/Stirling-PDFgithub.com/Stirling-Tools/Stirling-PDF
- TDiblik/main-gate-alprgithub.com/TDiblik/main-gate-alpr
- VikParuchuri/suryagithub.com/VikParuchuri/surya
- Walleclipse/ChineseAddress_OCRgithub.com/Walleclipse/ChineseAddress_OCR
Hacker News1 条
- Hacker News #37384327HN #37384327
HuggingFace2 条
- HF Space:opendatalab/DocLayout-YOLOhuggingface.co/spaces/opendatalab/DocLayout-YOLO
- HF:docs/transformershuggingface.co/docs/transformers/en/model_doc/layoutlm
其他外链5 条
- doc2x.noedgeai.comdoc2x.noedgeai.com/
- medium.com/@shivarama/layoutlmv3-from-zero-to-hero-part-1-85d05818eec4medium.com/@shivarama/layoutlmv3-from-zero-to-hero-part-1-85d05818eec4
- paddlejs.baidu.com/ocrpaddlejs.baidu.com/ocr
- pix2text.readthedocs.io/zh-cn/stable/commandpix2text.readthedocs.io/zh-cn/stable/command
- www.ocrarena.aiwww.ocrarena.ai/