Image Analysis

Extract text from images with OCR, detect PII and unsafe content, and get a redacted copy of the image back.

Authentication

Image endpoints require a user JWT (Authorization: Bearer YOUR_JWT).

Analyze an Image

POST /image-analysis/analyze

Runs OCR on the image, then scans the extracted text for PII and safety issues. When redaction applies, returns a redacted image.

Parameter	Type	Required	Description
`imageBase64`	string	Yes	Base64-encoded image (PNG, JPEG, …)
`ocr_language`	string	No	OCR language hint (e.g. `en`, `tr`)
`confidenceThreshold`	number	No	Minimum detection confidence, 0–1

cURL

curl -X POST https://api.cid222.ai/image-analysis/analyze \
  -H "Authorization: Bearer YOUR_JWT" \
  -H "Content-Type: application/json" \
  -d '{
    "imageBase64": "iVBORw0KGgoAAAANSUhEUg...",
    "ocr_language": "en"
  }'

Response

Returns the overall action, the extracted text, PII and safety detections, and (when redacted) the redacted image.

{
  "action": "mask",
  "extractedText": "Name: John Smith\nSSN: 123-45-6789",
  "piiDetections": [
    { "type": "PERSON_NAME", "value": "[PERSON_NAME]", "action": "mask", "confidence": 0.95 },
    { "type": "SSN", "value": "[SSN]", "action": "mask", "confidence": 0.99 }
  ],
  "safetyDetections": [],
  "wasRedacted": true,
  "redactedImageBase64": "iVBORw0KGgoAAAANSUhEUg...",
  "processingTimeMs": 1320
}

Redaction is optional

redactedImageBase64 is only present when a detection requires masking. extractedText and detections are always returned.

List OCR Engines

GET /image-analysis/ocr-engines

Returns the available OCR engines and their language support.

Compare OCR Engines

POST /image-analysis/compare-ocr

Runs the same image through multiple OCR engines so you can compare extraction quality.