Chile Passport OCR with the StructOCR Python SDK

Why Chilean Passport OCR is Difficult in Python

Building a reliable passport OCR pipeline from scratch is non-trivial for Chilean documents. The Chilean passport features a bilingual layout, combining Spanish and English text on the same data page. Spanish uses accented characters such as á, é, í, ó, ú, ü, and the distinctive ñ, which frequently cause misinterpretation in standard Python OCR libraries like Tesseract, leading to character corruption and field misalignment. Furthermore, the documents incorporate intricate security backgrounds, guilloche patterns, and the national coat of arms that introduce optical noise. Developing custom RegEx patterns in Python to parse the Machine Readable Zone (MRZ) while correcting these bilingual and accented-character alignment issues is highly brittle, often resulting in high manual review rates.

Enterprise-Grade Extraction with the StructOCR SDK

StructOCR simplifies document processing in your Python ecosystem by replacing complex pipelines with a single async API call. Our service leverages pre-trained Deep Learning models optimized specifically for Latin American identity documents and the complexities of Spanish/English bilingual typography. Our passport mrz ocr api automatically handles perspective correction, denoising, and glare removal. Instead of returning raw, unstructured text strings, the StructOCR Python SDK provides standardized JSON output with validated fields. This capability is crucial for applications managing international borders, as it eliminates the need for manual parsing, delivering production-ready data directly to your FastAPI, Django, or Flask applications. For the fastest Python integration, install the official StructOCR SDK and see the Python SDK documentation.

Production Use Cases

• Digital Onboarding (e-KYC): Reduce drop-off rates by pre-filling user data from Chilean Passports into your fintech or digital services apps in under 2 seconds.
• Travel & Aviation Apps: Seamlessly integrate with Python backends for automated check-in systems and border management at hubs like Arturo Merino Benítez International Airport (SCL) in Santiago.
• Financial Compliance: Ensure strict compliance with the Financial Market Commission (CMF) and regional Anti-Money Laundering (AML) regulations by automatically and accurately verifying identity documents.

Chile Passport OCR with the Python SDK

The official Python SDK handles file encoding, API communication, and structured passport results. Use the SDK directly or open the FastAPI tab for a server endpoint. Keep your API key in STRUCTOCR_API_KEY.

Prerequisite: `pip install structocr`; set the server-side `STRUCTOCR_API_KEY` environment variable.

Prefer another stack? Open the Node.js SDK + Express integration.

import os
from structocr import StructOCR

client = StructOCR(api_key=os.environ["STRUCTOCR_API_KEY"])


def scan_chile_passport():
    image_path = "chile_passport_sample.jpg"

    try:
        result = client.scan_passport(image_path)

        if result.get("success"):
            data = result["data"]
            print("Chile passport extraction successful")
            print(f"Passport #:  {data.get('passport_number')}")
            print(f"Name:        {data.get('given_names')} {data.get('surname')}")
            print(f"Nationality: {data.get('nationality')}")
            print(f"DOB:         {data.get('date_of_birth')}")
        else:
            print(f"Extraction failed: {result.get('error')}")
    except Exception as error:
        print(f"SDK error: {error}")


if __name__ == "__main__":
    scan_chile_passport()

Sample JSON Output

The Python SDK returns a dictionary matching this normalized JSON structure.

{
  "success": true,
  "data": {
    "type": "passport",
    "country_code": "CHL",
    "nationality": "CHL",
    "passport_number": "P12345678",
    "surname": "GONZÁLEZ",
    "given_names": "FELIPE ANDRÉS",
    "sex": "M",
    "date_of_birth": "1992-04-15",
    "place_of_birth": "SANTIAGO",
    "date_of_issue": "2023-08-20",
    "date_of_expiry": "2028-08-19",
    "issuing_authority": "SERVICIO DE REGISTRO CIVIL E IDENTIFICACIÓN"
  }
}