🚗 Thai Vehicle License Plate OCR

🚗 ระบบ OCR สำหรับอ่านป้ายทะเบียนรถยนต์

Welcome to Thai Vehicle License Plate OCR API, version 2.0, an AI product developed by iApp Technology Co., Ltd. Our API is designed to extract license plate numbers and vehicle information from images with high accuracy and speed. The API supports JPEG, JPG, PNG file formats and can process vehicle images in 1-2 seconds.

Try Demo

Visit our API Portal to test the Thai Vehicle License Plate OCR API with your own images.

Getting Started

Prerequisites
- An API key from iApp Technology
- Vehicle images containing license plates
- Supported file formats: JPEG, JPG, PNG
- Maximum file size: 2MB
Quick Start
- Fast processing (1-2 seconds per image)
- High accuracy text extraction (92.28% overall accuracy)
- Support for multiple vehicle brands and types
Key Features
- Detailed field extraction including:
  - License plate number
  - Vehicle brand
  - Vehicle type
  - Vehicle color
  - Province registration
- Vehicle detection
- Missing plate detection
- Flexible JSON response format
Security & Compliance
- GDPR and PDPA compliant
- No data retention after processing

How to get API Key?

Please visit API Portal to view your existing API key or request a new one.

Example

1. Sample Vehicle Real Life Application

Example 1

Vehicle

Example 2

Vehicle

Example 3

Vehicle

2. Sample Vehicle File

Vehicle

Request

curl --location 'https://api.iapp.co.th/license-plate-recognition/file' \
--header 'apikey: {YOUR API KEY}' \
--form 'file=@"{YOUR UPLOADED FILE}"'

Response

{
    "conf": 93.30192566,
    "country": "th",
    "infer_time(s)": 0.18,
    "is_missing_plate": "no",
    "is_vehicle": "yes",
    "lp_number": "กร5539",
    "message": "success",
    "province": "th-14:Phra Nakhon Si Ayutthaya (พระนครศรีอยุธยา)",
    "status": 200,
    "vehicle_body_type": "tractor-trailer",
    "vehicle_brand": "honda",
    "vehicle_color": "white",
    "vehicle_model": "honda_jazz",
    "vehicle_orientation": "135",
    "vehicle_year": "2010-2014"
}

Features & Capabilities

Core Features

License Plate Recognition: Extracts and accurately reads Thai license plate numbers from images.
Comprehensive Vehicle Information: Identifies and provides details such as:
- License plate number
- Registered province
- Vehicle make (brand)
- Vehicle model
- Manufacturing year
- Vehicle orientation (front, side, rear)
- Vehicle type (e.g., sedan, SUV, truck)
High Accuracy: Utilizes advanced computer vision algorithms to deliver precise recognition even in challenging lighting and environmental conditions.

Supported Capabilities

Real-Time Processing: Suitable for time-sensitive applications like toll collection and vehicle tracking.
Batch Processing: Efficiently handles multiple images for large-scale applications.
Environmental Adaptability: Works reliably across various scenarios, including low-light and high-glare environments.

Use Cases

Automatic Toll Collection: Streamline toll payment processes by recognizing vehicles and license plates in real time.
Parking Management Systems: Automate entry and exit logging for vehicles in parking facilities.
Vehicle Tracking: Enhance logistics and fleet management by integrating license plate recognition for vehicle identification.
Security and Surveillance: Improve security systems with vehicle-based tracking and identification.

Additional Capabilities

Easy Integration: Provides a RESTful API for seamless integration into existing applications.
Fast and Reliable: Delivers quick response times and consistent performance for real-world deployment.
Extensible and Scalable: Supports additional features and expansions as per evolving user requirements.

API Reference

Endpoint

POST https://api.iapp.co.th/license-plate-recognition/file

Headers

Name	Type	Description
apikey	String	API Key

Parameters

Name	Type	In	Required	Description
vehicle_image	object	body	Yes	Picture consists of a vehicle

Response Explanation

Parameters	Explanation
conf	Confidence score of the license plate recognition in percentage.
infer_time(s)	Time taken for inference in seconds.
is_missing_plate	Indicates if there is a license plate missing in the image. Possible values: "yes" or "no".
is_vehicle	Indicates if a vehicle is present in the image. Possible values: "yes" or "no".
lp_number	License plate number recognized from the image.
message	API response message. Possible values: "success" or "error".
province	Province of the registered vehicle as identified by the license plate.
status	HTTP status code of the API response.
vehicle_body_type	Body type of the recognized vehicle.
vehicle_brand	Brand of the recognized vehicle.
vehicle_color	Color of the recognized vehicle.
vehicle_model	Model of the recognized vehicle.
vehicle_orientation	Orientation of the recognized vehicle in the image.
vehicle_year	Year range of the recognized vehicle model.

Code Example

Python

import requests

url = "https://api.iapp.co.th/license-plate-recognition/file"

payload = {}
files=[
  ('file',('{YOUR UPLOADED FILE NAME}',open('{YOUR UPLOADED FILE PATH}','rb'),'image/png'))
]
headers = {
  'apikey': {YOUR API KEY}
}

response = requests.request("POST", url, headers=headers, data=payload, files=files)

print(response.text)

JavaScript

const axios = require('axios');
const FormData = require('form-data');
const fs = require('fs');
let data = new FormData();
data.append('file', fs.createReadStream('{YOUR UPLOADED FILE PATH}'));

let config = {
  method: 'post',
  maxBodyLength: Infinity,
  url: 'https://api.iapp.co.th/license-plate-recognition/file',
  headers: {
    'apikey': '{YOUR API KEY}',
    ...data.getHeaders()
  },
  data : data
};

axios.request(config)
.then((response) => {
  console.log(JSON.stringify(response.data));
})
.catch((error) => {
  console.log(error);
});

PHP

<?php

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://api.iapp.co.th/license-plate-recognition/file',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 0,
  CURLOPT_FOLLOWLOCATION => true,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_POSTFIELDS => array('file'=> new CURLFILE('{YOUR UPLOADED FILE PATH}')),
  CURLOPT_HTTPHEADER => array(
         'apikey: {YOUR API KEY}'
  ),
));

$response = curl_exec($curl);

curl_close($curl);
echo $response;

Swift

let parameters = [
  [
    "key": "file",
    "src": "{YOUR UPLOADED FILE PATH}",
    "type": "file"
  ]] as [[String: Any]]

let boundary = "Boundary-\(UUID().uuidString)"
var body = Data()
var error: Error? = nil
for param in parameters {
  if param["disabled"] != nil { continue }
  let paramName = param["key"]!
  body += Data("--\(boundary)\r\n".utf8)
  body += Data("Content-Disposition:form-data; name=\"\(paramName)\"".utf8)
  if param["contentType"] != nil {
    body += Data("\r\nContent-Type: \(param["contentType"] as! String)".utf8)
  }
  let paramType = param["type"] as! String
  if paramType == "text" {
    let paramValue = param["value"] as! String
    body += Data("\r\n\r\n\(paramValue)\r\n".utf8)
  } else {
    let paramSrc = param["src"] as! String
    let fileURL = URL(fileURLWithPath: paramSrc)
    if let fileContent = try? Data(contentsOf: fileURL) {
      body += Data("; filename=\"\(paramSrc)\"\r\n".utf8)
      body += Data("Content-Type: \"content-type header\"\r\n".utf8)
      body += Data("\r\n".utf8)
      body += fileContent
      body += Data("\r\n".utf8)
    }
  }
}
body += Data("--\(boundary)--\r\n".utf8);
let postData = body


var request = URLRequest(url: URL(string: "https://api.iapp.co.th/license-plate-recognition/file")!,timeoutInterval: Double.infinity)
request.addValue("{YOUR API KEY}", forHTTPHeaderField: "apikey")
request.addValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")

request.httpMethod = "POST"
request.httpBody = postData

let task = URLSession.shared.dataTask(with: request) { data, response, error in
  guard let data = data else {
    print(String(describing: error))
    return
  }
  print(String(data: data, encoding: .utf8)!)
}

task.resume()

Kotlin

val client = OkHttpClient()
val mediaType = "text/plain".toMediaType()
val body = MultipartBody.Builder().setType(MultipartBody.FORM)
  .addFormDataPart("file","{YOUR UPLOADED FILE NAME}",
    File("{YOUR UPLOADED FILE PATH}").asRequestBody("application/octet-stream".toMediaType()))
  .build()
val request = Request.Builder()
  .url("https://api.iapp.co.th/license-plate-recognition/file")
  .post(body)
  .addHeader("apikey", "{YOUR API KEY}")
  .build()
val response = client.newCall(request).execute()

Java

OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("text/plain");
RequestBody body = new MultipartBody.Builder().setType(MultipartBody.FORM)
  .addFormDataPart("file","{YOUR UPLOADED FILE NAME}",
    RequestBody.create(MediaType.parse("application/octet-stream"),
    new File("{YOUR UPLOADED FILE PATH}")))
  .build();
Request request = new Request.Builder()
  .url("https://api.iapp.co.th/license-plate-recognition/file")
  .method("POST", body)
  .addHeader("apikey", "{YOUR API KEY}")
  .build();
Response response = client.newCall(request).execute();

Dart

var headers = {
  'apikey': '{YOUR API KEY}'
};
var request = http.MultipartRequest('POST', Uri.parse('https://api.iapp.co.th/license-plate-recognition/file'));
request.files.add(await http.MultipartFile.fromPath('file', '{YOUR UPLOADED FILE PATH}'));
request.headers.addAll(headers);

http.StreamedResponse response = await request.send();

if (response.statusCode == 200) {
  print(await response.stream.bytesToString());
}
else {
  print(response.reasonPhrase);
}

Accuracy and Performance

Version 1.2 (2022-01-16)

Model Evaluation based on iApp-Vechicle image data (100 images)

Exact Match Accuracy

Model	Accuracy (%)
Vehicle Detection Model	99.00%
Vehicle License-plate Detection Model	99.00%
License-plate Character + Number Recognition Model	97.00%
License-plate Province Model	99.00%
Vehicle Brand	95.00%
Vehicle Color	85.00%
Vehicle Car Model	72.00%
Overall Accuracy	92.28%

Version 1.1 (2021-12-23)

Model Evaluation based on iApp-vehicle image data (118 images)

Exact Match Accuracy

Model	Accuracy (%)
Vehicle Detection Model	96.40%
Vehicle License-plate Detection Model	95.65%
License-plate Character + Number Recognition Model	94.82%
License-plate Province Model	90.67%
Vehicle Brand	81.30%
Vehicle Color	80.50%
Vehicle Car Model	66.10%
Overall Accuracy	86.49%

History/Change Logs

Version 1.0 - 2021-09-12

Added

First initial version, introducing iApp's license plate OCR.
This version also showcases the recognition of vehicle features:
- Vehicle type.
- Vehicle brand.
- Vehicle color.
- Province that the license plate is registered.
Accuracy of these parameters will be improved and released officially in the upcoming version.

Version 1.1 - 2021-12-23

Improved

Accuracy of the following parameters of the API system is improved

License plate number
Province
Vehicle type
Vehicle Color
Vehicle Brand
Vehicle model

Version 1.2 - 2023-01-16

Improved overall accuracy

License plate number
Province
Vehicle color
Vehicle brand
Vehicle model

Version 2.0 - 2023-02-16

Add new Features

New features were added as follows:

Vehicle body type
Vehicle year ranges
Vehicle orientation in a image
Is Vehicle Flag
Is Missing Plate Flag

Pricing

AI API Service Name	Endpoint	IC Per Request	On-Premise
Thai Vehicle License Plate Image Recognition (LPR)	iapp_license_plate_recognition_v1_base64	0.75 IC/Request	Contact
Thai Vehicle License Plate Image Recognition (LPR)	iapp_license_plate_recognition_v1_file	0.75 IC/Request	Contact

Getting Started​

Example​

1. Sample Vehicle Real Life Application​

2. Sample Vehicle File​

Request​

Response​

Features & Capabilities​

Core Features​

Supported Capabilities​

Use Cases​

Additional Capabilities​

API Reference​

Endpoint​

Headers​

Parameters​

Response Explanation​

Code Example​

Python​

JavaScript​

PHP​

Swift​

Kotlin​

Java​

Dart​

Accuracy and Performance​

Version 1.2 (2022-01-16)​

Version 1.1 (2021-12-23)​

Model Evaluation based on iApp-vehicle image data (118 images) ​

History/Change Logs​

Version 1.0 - 2021-09-12​

Version 1.1 - 2021-12-23​

Version 1.2 - 2023-01-16​

Version 2.0 - 2023-02-16​

Pricing​

Getting Started

Example

1. Sample Vehicle Real Life Application

2. Sample Vehicle File

Request

Response

Features & Capabilities

Core Features

Supported Capabilities

Use Cases

Additional Capabilities

API Reference

Endpoint

Headers

Parameters

Response Explanation

Code Example

Python

JavaScript

PHP

Swift

Kotlin

Java

Dart

Accuracy and Performance

Version 1.2 (2022-01-16)

Version 1.1 (2021-12-23)

Model Evaluation based on iApp-vehicle image data (118 images)

History/Change Logs

Version 1.0 - 2021-09-12

Version 1.1 - 2021-12-23

Version 1.2 - 2023-01-16

Version 2.0 - 2023-02-16

Pricing