Awesome Scanning

A curated list of awesome projects to simplify and improve paper scanning.

Tip

^{Sponsored by:}
Perspec - Desktop app to correct the perspective of images.
_{🌐 Get Perspec
🖥️ github.com/ad-si/Perspec}

---

Table Of Contents

• Websites
• Apps
  • Desktop
    • Cross Platform
    • MacOS
  • Mobile
    • iOS
  • Android
• Posts
• Discussions
• Software Libraries
• Document Management
• Research
  • Ishikawa Watanabe Laboratory - High-speed digital archiving
• Devices

Websites

• DIY Book Scanner - Community of people who build book scanners.
• Docutain - SDK for document & barcode scanning and data capturing.
• Eagle Doc - Invoice and receipt Recognition as a service.
• RoboEdit - Create ebooks from low quality scans with AI.

Apps

Desktop

Cross Platform

• Book Scanning - Book scanner software for home-made scanner (no license).
• BookDrive Editor Pro - Software for post-processing images of books (commercial).
• Voussoir - Single-camera solution for book scanning (open source).
• Booksorber - Processes camera images of book pages (commercial).
• Decapod - Web application frontend for image processing and capture tools.
• DxO Viewpoint - Correct perspective distortions in images (commercial).
• Easy Scan - Scanning software for book2net scanners (commercial).
• LIMB - Project inventory, image processing, quality control, OCR, document structuring and multiple format exporting for long-term archiving (commercial).
• Nidaba - Expandable and scalable OCR pipeline.
• OpenCV-Document-Scanner - Interactive document scanner built with Python and OpenCV.
• Page Improver - Automatic image enhancing software for page scanning.
• Perspec - Manually correct the perspective of images.
• Readiris 17 - OCR software to digitalize papers, images, or PDF files.
• ScanGate LWF - Stand-alone software for book digitization (commercial).
• ScanTailor - Interactive post-processing tool for scanned pages (open source).
• ScanTailor Advanced - Merges features of forks, adds new features, and includes fixes.
• Skarynka - Software to scan and process images to build books.
• YASW - Yet Another Scan Wizard (open source).
• scanner - Document scanner for the web built in Rust.

MacOS

• Plumb-Bob - Perspective rectifier (macOS app).
• Prizmo - Turn photos into scans by adjusting perspective, cropping, etc. (macOS app).

Mobile

iOS

• CamScanner - Scan any kind of document.
• Doc OCR - PDF scanner with document image dewarping.
• Doc Scan - Turn your iPhone / iPad into a portable scanner and PDF editor.
• Genius Scan - A scanner in your pocket.
• IRIScan - Scan documents with your iPhone or iPad. Trims, enhances and makes pictures of whiteboards and docs readable.
• Quick Scan - Scan, Recognize, Automate.
• Scanbot - High quality scans with one tap.
• Scannable - Scan contracts, receipts and business cards.
• Scanner Pro - Scan paper documents into PDFs.
• vFlat - Capture documents, forms, receipts, books and convert them into high-quality PDFs.

Android

• Adobe Scan - Scan, OCR, and edit documents (account required).
• Google Drive - Use the camera to scan documents (does not support loading existing photos).
• Microsoft Lens - Trim, enhances, and make photos of whiteboards and documents readable.
• Open Camera - Extensive open source camera app.
• PDF-Doc-Scan - Open source Android PDF document scanning app.

Posts

• Awesome Text Deskew - Collection of algorithms and Jupyter examples to deskew text.
• Dewarping pages
• Document scanner - How to Build a Kick-Ass Mobile Document Scanner in Just 5 Minutes.
• Genetic programming in the cloud
• Keypoint Detection with Transfer Learning
• math.stackexchange - Compute ratio of a rectangle seen from an unknown perspective.
• Noteshrink - Compressing and enhancing hand-written notes.
• Page dewarping - Flattening images of curled pages.
• Perspective transform - 4 Point OpenCV getPerspective Transform Example.
• Stackoverflow - Proportions of a perspective-deformed rectangle.
• Unpaper - Post-processing tool for scanned sheets of paper.
• pdfsandwich - CLI tool using OCR to add text to image PDFs.
• rbgg - Remove background from images of paper.
• Unprojecting text with ellipses - Using transformed ellipses to estimate perspective transformations of text.
• Document-Dewarping with Control-Points - Dewarping of document images using control points.
• Building an image processing pipeline with Python

Discussions

• Methods To Sense The 3D Surface/Structure Of A Book
• Robust Reading Competition - Detection and recognition challenges for text in scene images.
• What are the most common algorithms for adaptive thresholding?

Software Libraries

• CornerAPI - Detect torn corners and edges in document images.
• doc2text - Bulk detect text blocks and OCR scanned PDFs.
• Empty_training - Train neural network to detect empty pages in document images.
• EmptyAPI - Detect empty pages in document images.
• FaultyImageAPI - Combines CornerAPI, EmptyAPI, PostitAPI, and WritingtypeAPI
• imgwarp-js - Warp images using JavaScript.
• Laser Book Scanning - Experimental methods for dewarping document images based on the use of lasers.
• LCNN - End-to-End Wireframe Parsing.
• Perspectra - Automatically extract and perspectively correct documents from images.
• Pixelnetica - Document Scanning SDK for business apps.
• PostitAPI - Detect post-it/sticky notes in document images.
• PyThreshold - Implementations of state-of-the-art image thresholding algorithms.
• Segment Anything - AI model that can cut out any object in any image.
• Table_segmentation - Segment table structures and detect text content in document images.
• Train_document_classification - Train a neural network to classify input documents based on the type/format.
• Train_fault_detection - Train a neural network to detect faults (e.g. folded corners, sticky notes, …) in document images.
• Train_writing_type - Train a neural network to classify document images by writing type (handwritten, typewritten).
• WeScan - Library to add scanning functionalities to an iOS app.
• WritingtypeAPI - Classify document based on the writing type (handwritten, typewritten).

Document Management

• Docspell - Document management system for private and small business use.
• Hermes - Open source document management system by HashiCorp.
• Mayan EDMS - Libre document management system.
• OpenPaper.work - Scan and import personal documents.
• Paperless NGX - Scan, index, and archive paper documents.
• Papermerge - Open source document management system for digital archives.
• TagSpaces - Offline & open source document manager with tagging support.
• Teedy - Lightweight document management system for individuals & businesses.

Research

• Whiteboard scanning - Whiteboard scanning and image enhancement by Zhengyou Zhang , Li-Wei He
• Cam params - Determining camera parameters from the perspective projection of a rectangle by Robert M. Haralick. (PDF)
• Dewarping of document images - Two-Step Dewarping of Camera Document Images by N. Stamatopoulos, B. Gatos, I. Pratikakis & S. J. Perantonis
• Dewarping of Document Images using Coupled-Snakes
• DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks
• Image and Depth from a Conventional Camera with a Coded Aperture
• The IUPR Dataset of Camera-Captured Document Images
• Image processing via level set curvature flow
• OCR Datasets - Collection of OCR-related datasets.

Ishikawa Watanabe Laboratory - High-speed digital archiving

Vision architecture overview

• Book Flipping Scanning
• BFS-Auto: High Speed & High Definition Book Scanner
• Real-time 3D Page Tracking and Book Status Recognition
• High-speed and High-definition Document Digitalization System based on Adaptive Scanning using Real-time 3D Sensing
• Automatic page turner machine for Book Flipping Scanning
• Document Digitization and its Quality Improvement using a Multi-camera Array
• Digitization of Deformed Documents using a High-speed Multi-camera Array
• BFS-Solo: High Speed Book Digitization using Monocular Video
• Reconstruction of 3D Surface and Restoration of Flat document Image from Monocular Image Sequence
• High-accuracy rectification technique of deformed document image using Tiled Rectangle Fragments (TRFs)
• Document Image Rectification using Advance Knowledge of 3D Deformation
• Estimation of Non-rigid Surface Deformation using Developable Surface Model
• Proof-of-concept prototype for Book Flipping Scanning

Devices

• Archivist - V-shaped platner based book scanner (open source).
• book2net - Book scanners for libraries and archives (commercial).
• Linear Book Scanner - Low-cost page-turning book scanner (open source).
• Portable Scanners - Several portabal scanning devices (commercial).