Farsi OCR

Why Farsi OCR Is Challenging

• Right-to-left script with bidirectional text when Persian is mixed with Latin characters or numbers
• Supporting both Nastaliq (calligraphic, diagonal) and Naskh (horizontal baseline) Persian typefaces
• Recognizing Persian-specific characters (پ, چ, ژ, گ) that extend the Arabic character set
• Handling the Persian ی and ک which differ visually from their Arabic counterparts (ي, ك)
• Processing documents with Persian numerals (۰-۹) alongside or instead of Western digits
• Correctly interpreting Ezafe construction markers which are often omitted in print

How to Extract Farsi Text from a PDF & Images

1. Go to fastocr.org
2. Upload your Farsi image or PDF. Language is detected automatically.
3. Wait for processing — images take seconds, PDFs show a progress bar.
4. Download results: searchable PDF, raw text file, or copy text directly.

Tips for Better Farsi OCR Accuracy

1. Use Naskh-style fonts for source documents — OCR accuracy is significantly higher than on Nastaliq
2. Scan at 300 DPI minimum to preserve dots distinguishing Persian characters like پ, چ, ژ, گ
3. Verify Persian-specific ی and ک are not replaced with Arabic ي and ك in the output
4. For documents with Persian numerals (۰-۹), check that they are not converted to Arabic or Western digits
5. Separate multi-column layouts and remove decorative borders before processing

Common Use Cases for Farsi OCR

• Digitizing Iranian legal documents, contracts, and court rulings
• Extracting text from Persian academic publications and university theses
• Processing Iranian government forms, identity documents, and official certificates
• Converting scanned Persian literary works, poetry collections, and historical texts
• Archiving Persian-language business records, invoices, and financial documents

Frequently Asked Questions