Optical character recognition
Links
- Tesseract OCR - Tesseract Open Source OCR Engine (main repo).
- Tesseract.js - JavaScript library that gets words in almost any language out of images.
- keras-ocr - Packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.
- Awesome Scanning - Curated list of awesome projects to simplify and improve paper scannning.
- Awesome OCR
- Scale Document - Secure platform for document processing.
- Easy OCR - Ready-to-use OCR with 40+ languages supported including Chinese, Japanese, Korean and Thai. (HN)
- OCRmyPDF - Adds an OCR text layer to scanned PDF files, allowing them to be searched. (Docs)
- OCR with Keras, TensorFlow, and Deep Learning (2020)
- What's so hard about PDF text extraction? (2020) (HN)
- FilingDB - Database of extracted and structured text from European company filings. Optimised for quant investors.
- InvoiceNet - Deep neural network to extract intelligent information from invoice documents.
- PaddleOCR - Rich, leading, and practical OCR tools that help users train better models and apply them into practice. (Web) (HN)
- TextRecognitionDataGenerator - Synthetic data generator for text recognition.
- Paperless - Index and archive all of your scanned paper documents.
- Tesseract Teaser
- macOCR - Get any text on your screen into your clipboard. (HN)
- Solving direct text extraction from PDFs (2021)
- MMOCR - OpenMMLab Text Detection, Recognition and Understanding Toolbox.
- In-Browser OCR (HN)
- Project Naptha - Highlight, copy and translate text from any image in the browser. (HN)
- Extract Table - API for extracting a table from an image. (Code)
- Amazon Textract - Easily extract printed text, handwriting, and data from any document. (Code Samples)
- CalamariOCR - Line based ATR Engine based on OCRopy.
- Rust WebAssembly OCR experiments (2022)
- Paperless-NGX - Supercharged version of paperless: scan, index and archive all your physical documents. (HN)
- scan2drive - Go program (with a web interface) for scanning, converting and uploading physical documents to Google Drive.
- docTR - Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch.
- RapidOCR - Cross platform OCR Library based on PaddleOCR & OnnxRuntime.
- meme_finder - Find locally-saved memes via their meme text using OCR. Written in Rust.
- Veryfi OCR API - OCR API for Real-Time Data Extraction from Receipts & Invoices. (Node SDK)
- ocrit - Command-line utility for performing OCR using Apple's Vision framework.
- Tesseract WASM - WebAssembly build of the Tesseract OCR engine for use in the browser and Node.
- tinyocr - Tiny command line OCR utility for recent versions of MacOS.
- Our search for the best OCR tool (2019) (HN)
- Building an OCR solution for document analysis with AWS Textract and AWS StepFunctions
- Donut - Document Understanding Transformer. (HN)
- ocrpy - OCR, Archive, Index and Search: Implementation agnostic OCR framework.
- Tesseract server (OCR over HTTP) - Small lightweight HTTP server that converts photos, images and scanned documents to text using optical character recognition by utilizing the power of Google Tesseract.
- Technical Report on Web-based Visual Corpus Construction for Visual Document Understanding (2022) (Code)
- Text Finder - Image-to-text (OCR) app that works offline. Powered by tesseract.js.
- OCR at Edge on Cloudflare Constellation (2023) (HN)
- Awesome OCR