Supported File Formats

Images

• JPEG
• PNG
• TIFF
• BMP
• GIF
• Scanned PDF

Batch OCR

• Multi-page PDF
• DjVu
• ZIP
• Folder

Recognition results

• Text
• PDF
• Microsoft Word
• Microsoft Excel
• HTML
• RTF
• ePub
• JSON
• XML
• CSV

Advanced .NET OCR API Features

• Photo OCR - Extract text from smartphone photos with scan-level accuracy.
• Searchable PDF - Convert any scan into a fully searchable and indexable document.
• URL recognition - Recognize an image from URL without downloading it locally.
• Bulk recognition - Read all images from multi-page documents, folders and archives.
• Any font and style - Identify and recognize text in all popular typefaces and styles.
• Fine-tune recognition - Adjust every OCR parameter for best recognition results.
• Spell checker - Improve results by automatically correcting misspelled words.
• Mathematical formula detection - Accurately detect and recognize complex mathematical expressions.
• Text search and image-to-image comparison - Search for text or patterns in images, or compare the recognized text from two images.
• AI-powered correction - Fix misrecognized words and grammar using transformer-based LLMs - no custom training required.
• Semantic postprocessing - Go beyond characters: refine noisy OCR output with LLMs for improved content quality and language normalization.
• Plug-in LLM pipelines - Connect external language models to correct OCR recognition mistakes and restore incomplete or fragmented text.
• 140+ recognition languages - Aspose's .NET OCR library is a universal solution for document processing, data extraction, and content digitization on a global scale. You can recognize documents written in mixed languages, such as Chinese/English, Arabic/French or Cyrillic/English. The following languages are supported:
  • Extended Latin: English, Spanish, French, Indonesian, Portuguese, German, Vietnamese, Turkish, Italian, Polish, and 80+ more.
  • Cyrillic alphabet: Russian, Ukrainian, Kazakh, Bulgarian, including mixed Cyrillic/English texts.
  • Arabic, Persian, Urdu, including texts mixed with English.
  • Chinese, Korean, Japanese, Devanagari, and Dravidian languages, including Hindi, Tamil, Marathi, and others.