Image Redaction — Protect PII in Images
Automatically detect and redact personal information in scanned documents, photos, and screenshots. Powered by Tesseract OCR with 38 language support.
How Image Redaction Works
From upload to redacted output in seconds
Upload Image
Upload a scanned document, photo, or screenshot
OCR Processing
Tesseract extracts text and character positions
PII Detection
Our engine identifies 320+ entity types using 317 regex recognizers and NLP
Redact & Download
PII is covered with colored bounding boxes
Image Redaction Features
Enterprise-grade image anonymization built on Tesseract OCR
Tesseract OCR Detection
Industry-standard OCR engine extracts text with character-level positioning for precise bounding-box redaction.
38 OCR Languages
Full Tesseract language pack support including Latin, Cyrillic, CJK, Arabic, and Devanagari scripts.
320+ Entity Types
Detect names, dates, addresses, phone numbers, IBANs, national IDs, tax numbers, and more across 70+ countries using 317 regex recognizers plus NLP.
Batch Processing
Process entire folders of scanned documents at once with parallel OCR and redaction.
Auto Orientation
EXIF orientation metadata is automatically applied before OCR to handle rotated or flipped images.
Multi-Format Support
Process PNG, JPEG, TIFF, BMP, WebP, and other common image formats with automatic conversion.
Supported Formats
Image Formats
- PNG
- JPEG / JPG
- TIFF
- BMP
- WebP
- GIF
Document Scans
- Scanned PDFs (rasterized)
- Faxed documents
- Photographed contracts
- ID card scans
Screenshots
- Desktop screenshots
- Mobile captures
- Browser screenshots
- Application windows
Frequently Asked Questions
How accurate is the OCR detection?
Tesseract OCR achieves 95%+ accuracy on clean, high-resolution documents. Lower-quality scans may have reduced accuracy. We automatically apply EXIF orientation correction and image preprocessing to optimize results.
What image formats are supported?
We support PNG, JPEG, TIFF, BMP, WebP, and GIF formats. Scanned PDFs are rasterized and processed as images. Maximum file size is 10MB per image, maximum resolution is 150 megapixels.
Which OCR languages are available?
38 Tesseract language packs are installed including English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian, Chinese, Japanese, Korean, Arabic, Hindi, and 24 more.
Can I process multiple images at once?
Yes! Batch processing is available on all plans. Free tier allows 5 images per batch, Professional 25, and Enterprise 100. Images are processed in parallel for maximum speed.