Vehicle Registration Book OCR

Reads a Thai vehicle registration book and returns the vehicle and its ownership.

POST/ocr/v3/vehicle-registration/fileTry it

• Price1 ICper page
• Measured93.4%
• Served29Kcalls

• v1.0
• Active
• Benchmark paper (PDF)

Input

OutputPOST /ocr/v3/vehicle-registration/file

registration_date

27 มิถุนายน 2562

license_plate

1กข 1234

province

กรุงเทพมหานคร

vehicle_type

รถยนต์นั่งส่วนบุคคลไม่เกิน 7 คน

brand

ISUZU

model

mu-X

year

2019

color

ขาว

body_number

MP1TFR85XKT000000

engine_number

4JJ1XX0000

fuel_type

ดีเซล

seating_capacity

7

owner_name

นายสมชาย ตัวอย่าง

owner_id

1100000000001

owner_address

123 ถนนพหลโยธิน แขวงจตุจักร เขตจตุจักร กรุงเทพมหานคร

occupant_name

—

occupant_id

—

Every field, under Response

Request

curl -X POST "https://api.iapp.co.th/ocr/v3/vehicle-registration/file" \
  -H "apikey: YOUR_API_KEY" \
  -F "file=@/path/to/document.pdf" \
  -F "target_lang=th" \
  -F "include_confidence=true"

Response

200OK. The fields are explained under Response.

{
    "docs": [
        {
            "message": "success",
            "raw": {},
            "processed": {
                        "registration_date": "27 มิถุนายน 2562",
                        "license_plate": "1กข 1234",
                        "province": "กรุงเทพมหานคร",
                        "vehicle_type": "รถยนต์นั่งส่วนบุคคลไม่เกิน 7 คน",
                        "brand": "ISUZU",
                        "model": "mu-X",
                        "year": 2019,
                        "color": "ขาว",
                        "body_number": "MP1TFR85XKT000000",
                        "engine_number": "4JJ1XX0000",
                        "fuel_type": "ดีเซล",
                        "seating_capacity": 7,
                        "owner_name": "นายสมชาย ตัวอย่าง",
                        "owner_id": "1100000000001",
                        "owner_address": "123 ถนนพหลโยธิน แขวงจตุจักร เขตจตุจักร กรุงเทพมหานคร",
                        "occupant_name": null,
                        "occupant_id": null
            },
            "confidence": {
                        "registration_date": 0.95,
                        "license_plate": 0.95,
                        "province": 0.95,
                        "vehicle_type": 0.95,
                        "brand": 0.95,
                        "model": 0.95
            },
            "process_ms": 4120
        }
    ],
    "docs_count": 1,
    "process_ms": 4300
}

Request

multipart/form-data only; there is no Base64 form. Every page of a PDF is read and billed.

Headers

apikeystringrequired

Your API key, created under API Keys in the control panel.

Body

filefilerequired

The registration book. PDF, JPEG, PNG or WEBP, up to 50 MB. Repeatable: several documents in one request.

return_ocrboolean

true to include the raw OCR text.

target_langstring

The language of the extracted values: th, the default, en, or auto to keep the document's own language.

include_confidenceboolean

Default true: a confidence from 0.00 to 1.00 per field.

/v3/store/ocr/vehicle-registration is the same endpoint under the store prefix.

Response

The iapp-input-pages header carries the number of pages billed.

docsarray

One entry per document read

docs.processedobject

The fields read from the document

docs.processed.registration_datedocs.processed.license_platedocs.processed.province

When registered, the plate, and the province of registration

docs.processed.vehicle_typedocs.processed.branddocs.processed.modeldocs.processed.yeardocs.processed.color

The vehicle: type, make, model, model year (CE), colour

docs.processed.body_numberdocs.processed.engine_numberdocs.processed.fuel_typedocs.processed.seating_capacity

The chassis and engine numbers, the fuel, the seats

docs.processed.owner_namedocs.processed.owner_iddocs.processed.owner_address

The most recent registered owner: name, national or juristic ID, address

docs.processed.occupant_namedocs.processed.occupant_id

The possessor, if any

docs.messagestring

Status message

docs.rawobject

The OCR text, when requested

docs.confidenceobject

Confidence per field, 0 to 1

docs.confidence.registration_datenumber

docs.confidence.license_platenumber

docs.confidence.provincenumber

docs.confidence.vehicle_typenumber

docs.confidence.brandnumber

docs.confidence.modelnumber

docs.process_msinteger

Processing time, in milliseconds

docs_countinteger

Number of documents read

process_msinteger

Processing time, in milliseconds

Status codes

Code	Meaning
400	Unsupported file extension, or a file over 50 MB
404	Unknown document type in the URL
422	No file attached
500	Processing error; the response carries a code to quote to support
502	Temporary processing failure, also when any page of a multi-page file fails (code: PROCESSING_FAILED). Not charged; retry
503	Service busy (PROCESSING_BUSY). Not charged; retry, after the seconds in Retry-After when that header is present
504	Processing timed out (PROCESSING_TIMEOUT). Not charged; retry

Details

Measured

On the production service, 28 October 2026, against a synthetic test set: 40 vehicle registration book pages with invented values and a specimen watermark, 20 degraded as office scans and 20 as phone photographs. Real documents, with stamps, handwriting and unfamiliar layouts, score lower.

Measure	Result
Fields exactly right, 623 fields	93.4% (95% CI 91.9–95.1)
Pages with every field right	27.5%
Registration date, vehicle type, make, year, colour, fuel, seats	100.0% each
Plate, province, model	95.0%, 97.5%, 97.5%
Owner's name, ID, address	92.5%, 97.5%, 95.0%
Engine number, 33 pages	90.9%
Chassis number (body_number)	32.5%
Median time per page through the API, 44 documents across the 11 types	10.8 s (19.9 s at the 95th percentile)

The chassis number was right on 13 of 40 pages. The errors are 0 read as O and 8 read as B: 13 answers contained I, O or Q, letters a chassis number never uses. The test typeface draws these characters alike, so real books may fare better, but check body_number against its alphabet and length before use. Method, every field and the errors: the benchmark (PDF).

Limits

• Up to 50 MB per request.
• Only the fields above are extracted.
• Degraded scans, glare and handwriting over printed values lower accuracy. Prefer the original PDF, a square-on photograph in even light, or a scan at 300 dpi or more.
• The per-field confidence does not mark errors (0.957 on wrong fields against 0.967 on right ones in the benchmark), so do not use it to choose fields for review; check identifiers against their format and the check digit of owner_id instead.

Data handling

Consent and notice under PDPA and GDPR remain with you as the data controller.