egdels/makeacopy

MakeACopy is an open-source document scanner app for Android that allows you to digitize paper documents with OCR functionality. The app is designed to be privacy-friendly, working completely offline without any cloud connection or tracking.

What it solves

MakeACopy is an offline document scanner for Android that allows users to digitize paper documents into searchable PDFs without relying on cloud services, telemetry, or tracking. It provides a privacy-focused alternative to cloud-based scanners like Microsoft Lens, specifically designed for users who want full control over their data and integration with self-hosted storage systems.

How it works

The app processes everything locally on the device. It uses a custom-trained machine learning model (via ONNX Runtime) and OpenCV for automatic document edge detection and perspective correction. For text recognition, it offers two OCR backends: PaddleOCR (in the published version) and Tesseract (in a legacy version). The app bundles necessary language models and fonts locally to ensure it remains fully functional offline.

Who it’s for

It is designed for privacy-conscious Android users and those who maintain self-hosted document archives (e.g., using paperless-ngx, Nextcloud, or Syncthing) who need a reliable, auditable way to scan documents.

Highlights

  • 100% Offline: No internet connection or cloud dependencies required for any feature.
  • Searchable PDFs: Converts scans into PDFs with embedded recognized text.
  • ML-Powered Detection: Uses an ONNX model for automatic document corner detection.
  • Multi-language Support: Supports OCR for 23 languages across various scripts, including CJK, Arabic, and Devanagari.
  • Inbox Mode: Automatically saves scans to a specific folder for seamless integration with self-hosted sync tools.
  • Accessibility Mode: Includes spoken and haptic feedback and hardware volume key shutter support.

Related

  • Project
    pynicolas/FairScan

    An open-source Android document scanner that uses local machine learning for automatic document detection and perspective correction to create private PDFs.

  • Project
    SubhamTyagi/android-ocr

    A privacy-focused Android application that uses Tesseract 5 to perform offline optical character recognition (OCR) in over 120 languages.

  • Project
    ocrmypdf/OCRmyPDF

    A command-line tool that adds an OCR text layer to scanned PDF files, making them searchable and copy-pasteable while maintaining original image resolution.

  • Project
    privatenumber/mac-ocr

    A macOS command-line tool and Node.js API for local, private OCR that extracts text from images and PDFs and creates searchable PDFs using Apple's Vision framework.

  • Project
    scribeocr/scribeocr

    A browser-based web application for recognizing text from images, proofreading OCR data with high precision, and creating fully digitized, ebook-style documents.