C# .NET OCR Library

Detect, identify, and extract document elements with a C# OCR library powered by machine learning (ML) and artificial intelligence (AI). With support for more than 100 different file types, you have the flexibility to convert the most common images and scanned documents into searchable PDFs. Leverage automatic image correction and preprocessing to improve OCR accuracy (automatic deskew, invert, noise removal, and more). Explore our guides and code samples to learn how you can quickly integrate our OCR technology into your application or workflow.

Try for Free Launch Demo

PSPDFKit SDKs are deployed in some of the world’s most popular applications, such as those made by Autodesk, Disney, UBS, Dropbox, IBM, and Lufthansa.

Key Capabilities

  • Highly accurate AI- and ML-powered OCR engine

  • Supports more than 100 languages and 100 file types

  • Built-in multithreading to make OCR significantly faster

  • Automatic preprocessing and image correction for poorly scanned documents

  • Output as text, searchable PDFs, or structured data

  • Zonal OCR to recognize text in a specific region within a document page

  • ML-based document recognition to automatically identify invoices, checks, and any structured document

  • Full Unicode support

Guides for OCR

Image to Searchable PDF
How to convert an image into a searchable PDF

PDF to Searchable PDF
How to convert a PDF into a searchable PDF

Deskew
How to auto-deskew files with preprocessing

Auto-Invert
How to auto-invert files with preprocessing

Enhance Characters
How to auto-enhance characters with preprocessing

Remove Noise
How to automatically remove noise and blemishes from documents

Remove Lines
How to automatically remove lines from documents

Remove Punch Holes
How to automatically remove punch holes from documents

Zonal OCR
How to OCR a specific region of a page

Free Trial

Start your free trial for unlimited access and expert support.