Beyond the Address: Extracting ECR Status and File Numbers from Indian Passports

Why generic OCR fails at strict Indian KYC compliance, and how specialized APIs capture every critical edge-case field.

Executive Summary for Developers

Strict Indian KYC compliance often requires data beyond the basic name and address, including the ECR (Emigration Check Required) status, File Number, and Old Passport details located on the back page. Generic OCR tools like Tesseract or Google Vision simply output raw text and frequently miss these edge-case fields entirely. StructOCR provides a domain-specific Indian Passport REST API. By sending a Base64 image payload, the API's spatial intelligence specifically hunts down and mathematically validates these unique Indian KYC fields, returning them in perfectly structured JSON.

Edge-Case Field Extraction Matrix

KYC Data FieldGeneric OCR (Tesseract / Cloud Vision)StructOCR Indian Passport API
ECR Status (Emigration Check Required)Usually missed or confused with background stampsSpecifically targeted and returned as a explicit boolean or string value (`ecr_status`)
File Number & Old Passport DataBlended into the address block as random alphanumeric noiseIsolated, parsed, and validated against standard Indian government formats
Lamination Glare ResistanceFails completely; glare blinds the text extractorContrast-normalization algorithms pierce through heavy Indian passport lamination
Integration MethodRequires massive backend Regex pipelines to find hidden fieldsZero parsing required. Direct Base64 API upload yields immediate nested JSON

The Compliance Gap in Generic OCR

When building fintech or travel onboarding flows for Indian citizens, extracting the name and address is just the baseline. True compliance often requires capturing the File Number (a unique 15-character alphanumeric code), Old Passport details, and determining the ECR (Emigration Check Required) status. Because these fields are scattered across the heavily laminated back page and often overlapping with official stamps, generic OCR engines fail miserably. They read the characters as random noise and lump them into the address paragraph, forcing developers to write impossible Regex rules to try and hunt them down.

Spatial Intelligence Built for India

StructOCR closes this compliance gap by treating the Indian passport as a specialized schema. Because it is a domain-aware API, it doesn't just read text from top to bottom; it uses spatial intelligence to look for specific visual anchors. It knows exactly where the File Number is typically printed and what its format should be. Instead of downloading heavy SDKs, your application simply converts the scanned image into a Base64 string and posts it to our Cloudflare-backed endpoint. The API cuts through the lamination glare and returns every edge-case field cleanly nested in the `country_specific.last_page` JSON object.

Implementation: Accessing Indian Edge-Case Fields

See how StructOCR neatly isolates complex fields like `ecr_status` and `file_no` that generic OCR tools completely miss.

JSON EXAMPLE
// StructOCR automatically isolates Indian-specific KYC fields
{
  "success": true,
  "data": {
    "country_code": "IND",
    "passport_number": "Z1234567",
    "country_specific": {
      "last_page": {
        "father_name": "AMIT SHARMA",
        "address": "FLAT 4B, GREENWOOD APARTMENTS, NEW DELHI PIN: 110001, INDIA",
        "old_passport_number": "P7654321",
        "old_passport_issue_date": "2010-01-05",
        "old_passport_issue_place": "DELHI",
        "file_no": "DL1076071103622",
        "ecr_status": null
      }
    }
  }
}

Ready to Build with StructOCR?

Get your API key in under a minute. New users receive 200 free credits to test Passport, VIN, Lincense Plate, Container, Receipt, HIN, Driver License, ID Card, Vehicle Registration, ATM Cassette and Invoice OCR APIs.

Start FreeOCR Playground

✓ No credit card required · ✓ Instant API key · ✓ Full API access