Automatically detect and locate redacted content in PDFs using advanced vision AI. Identifies black boxes, white-out areas, blur effects, and other obscuration methods with precise bounding box coordinates. Perfect for compliance verification and document audit trails.
// Detect all redacted content in a document
const formData = new FormData();
formData.append('document_file', pdfFile);
formData.append('include_coordinates', 'true');
const response = await fetch('/api/strikethroughs', {
method: 'POST',
headers: { 'X-API-Key': 'your-api-key' },
body: formData
});
const result = await response.json();
// Get all detected redactions with coordinates
console.log('Total redactions found:', result.redacted_items.length);
result.redacted_items.forEach(item => {
console.log('Redaction found on page:', item.page);
console.log('Bounding box:', item.bbox); // [x1, y1, x2, y2, x3, y3, x4, y4]
console.log('Confidence:', item.confidence); // 0.0-1.0
console.log('Reason:', item.reason); // Why it was detected as redacted
});
// Page metadata
console.log('Pages processed:', Object.keys(result.page_metadata).length);Detects black boxes, white-outs, blur effects, and other obscuration methods
Get exact bounding box coordinates for every redacted area
Efficiently processes entire documents with intelligent batching
Loading document viewer...
Vision AI for compliance and audit workflows
Detect all redacted content automatically with precise coordinates and confidence scores. Perfect for compliance verification and document audit trails.
Automatically verify redactions in Freedom of Information Act responses
Common uses:
Detect improperly redacted content
Verify complete obscuration
Audit legal documents for proper redaction before disclosure
Common uses:
Pre-filing redaction checks
Discovery document verification
Ensure PII and sensitive data are properly redacted before sharing
Common uses:
GDPR compliance verification
HIPAA redaction auditing
Create comprehensive records of redacted content locations
Common uses:
Redaction location mapping
Audit trail generation
Why automation beats manual verification
Stop manually reviewing every page. Use vision AI to automatically detect and locate all redacted content.
Unique: Vision AI automatically detects black boxes, white-outs, blur effects, and other obscuration methods with precise coordinates
| NinjadocAI | Template OCR | Generic LLM/AI API | |
|---|---|---|---|
❓Natural Language Questions | ~ | ||
📍Answer + Coordinate Proof | ~ | ||
⚡5-Minute Integration | ~ | ||
💲Transparent Pricing | ~ | ||
🔧TypeScript SDK + React Components | |||
🧠Context Understanding | ~ | ||
🎯Zero Configuration Required | ~ | ||
📐Handles Document Layout Variations | ~ | ||
🔌Developer-Friendly REST API | ~ |
Everything you need to know
The API uses advanced vision AI to detect solid black boxes, white-out areas, blur effects, color overlays, and other common obscuration methods. It returns precise bounding box coordinates and confidence scores for each detected redaction.
Our vision AI achieves 95%+ accuracy in detecting redacted content. Each detection includes a confidence score (0.0-1.0) and a reason explaining why it was identified as redacted, allowing you to filter results based on your accuracy requirements.
Each redaction includes: precise bounding box coordinates (quadrilateral with 8 floats), page number (1-indexed), confidence score (0.0-1.0), and a brief explanation of why it was identified as redacted.
Redaction detection costs 2 credits per page, with coordinates always included. For example, scanning a 50-page document costs 100 credits ($1.00). Credits never expire.
Yes! The API is designed for compliance use cases including FOIA processing, GDPR verification, HIPAA auditing, and legal document review. The coordinate data provides audit trails showing exactly where redactions were detected.
Documents can be up to 10MB in size and up to 50 pages per request. For larger documents, you can split them into multiple requests.
Complete your document intelligence toolkit