Thai Bank Book OCR

1.25 ICper page

v1.1.1-20260823 Active Since Aug 2022 Updated 23 Aug 2026 29,000 pages/hour 96.8% account number Whitepaper (PDF) POST /v3/store/ekyc/book-bank

Mobile & Web SDK available

Skip the camera work — our free open-source eKYC SDK (Web, Flutter, iOS, Android & React Native) auto-captures documents and faces and calls this API for you. View on GitHub.

The Thai Bank Book OCR API extracts the bank name, account number, account name, and branch from Thai bank passbook images, and detects whether the page carries a signature. It supports passbooks from the major Thai banks. The production service processes a page in 0.2 seconds (median) and sustains 29,000 pages per hour; see Accuracy for what to rely on and what to treat as advisory.

Live Demo

Upload a Thai bank passbook image, or use the synthetic specimen below.

Try Our AI Demo

Login or create a free account to use this AI service demo and explore our powerful APIs.

Get 100 Free Credits (IC) when you sign up!

Offer ends December 31, 2025

Create Free AccountLogin

Example Images (Click to try)

Try Demo

API Key

Log in to use your API keys or Create an account

Endpoint URL

cURL Command

Upload Image Book bank

Try the SDK (Live Camera)

Prefer not to upload a file? The free open-source iApp eKYC Web SDK captures the bank book automatically from your camera — it detects the page boundary, waits for a sharp stable frame, perspective-corrects the image, and submits it to this API. See more flows on the full SDK live demo page.

Loading live demo…

Quick Start

You need an API key from the API Key Management page. Send the image as multipart/form-data:

curl -X POST https://api.iapp.co.th/v3/store/ekyc/book-bank \
  -H "apikey: YOUR_API_KEY" \
  -F "file=@bankbook.jpg"

{
    "status": "success",
    "bank_name": "ไทยพาณิชย์ (SCB)",
    "account_number": "0123456789",
    "account_name": "บริษัท ไอแอพพ์เทคโนโลยี จำกัด",
    "bank_branch": "ฟิวเจอร์ พาร์ค รังสิต",
    "signature_detected": true
}

Endpoints and Pricing

Endpoint	Output	Price
POST /v3/store/ekyc/book-bank	JSON with bank name, account number, account name, branch, and signature detection	1.25 IC per page

The legacy paths /book-bank-ocr and /book-bank-ocr/file remain supported at the same price. For on-premise deployment, see Data Security.

Performance

Measured on the production service, August 2026.

Metric	Value
Median processing time	0.2 s per page
Sustained throughput	8.2 pages per second (29,000 pages per hour)
Maximum file size	10 MB
Supported input formats	JPEG, JPG, PNG
Supported banks	SCB, Bangkok Bank, Krungthai, Kasikorn, Krungsri, TMB

Accuracy

Field	Accuracy
Bank name	99.5%
Account number	96.8%
Account name	52.6%
Bank branch	63.1%

Rely on the machine-readable fields — bank name, account number, and account type — and treat the free-text account_name and bank_branch as advisory: passbooks vary widely in layout, print quality, and wear, so verify those two against another source when they matter. The recognition engine was upgraded in August 2026 and audited field by field against the previous engine on identical passbook images: 99.45 percent overall agreement, with the account number, bank name, and account type identical on every book tested, and no field removed or changed type. Details in the whitepaper:

Download the engine audit whitepaper (PDF)

Data Security and Compliance

• The service is GDPR and PDPA compliant.
• Uploaded images are processed in memory and are not retained after the response is returned.
• A fully self-contained on-premise deployment is available, in which no passbook data leaves your infrastructure. Contact us for details.

Technical Reference

Request

POST with multipart/form-data and the apikey header.

Parameter	Required	Description
file	Yes	Thai bank passbook image (the account-information page)

Response

{
    "status": "success",
    "processing_time": 0.2,
    "bank_name": "ไทยพาณิชย์ (SCB)",
    "account_number": "0123456789",
    "account_name": "บริษัท ไอแอพพ์เทคโนโลยี จำกัด",
    "bank_branch": "ฟิวเจอร์ พาร์ค รังสิต",
    "signature_detected": true
}

Response Fields

Field	Type	Description
status	String	success or an error status
processing_time	Float	Processing time in seconds
bank_name	String	Issuing bank
account_number	String	Account number
account_name	String	Account holder name (advisory — see Accuracy)
bank_branch	String	Branch name (advisory — see Accuracy)
signature_detected	Boolean	Whether a handwritten signature was found on the page

Code Examples

cURL

curl -X POST https://api.iapp.co.th/v3/store/ekyc/book-bank \
  -H "apikey: YOUR_API_KEY" \
  -F "file=@bankbook.jpg"

Python

import requests

url = "https://api.iapp.co.th/v3/store/ekyc/book-bank"
headers = {"apikey": "YOUR_API_KEY"}
files = {"file": open("bankbook.jpg", "rb")}

response = requests.post(url, headers=headers, files=files)
print(response.json())

JavaScript

const axios = require("axios");
const FormData = require("form-data");
const fs = require("fs");

const data = new FormData();
data.append("file", fs.createReadStream("bankbook.jpg"));

axios.post("https://api.iapp.co.th/v3/store/ekyc/book-bank", data, {
    headers: { apikey: "YOUR_API_KEY", ...data.getHeaders() },
})
    .then((response) => console.log(response.data))
    .catch((error) => console.log(error));

PHP

<?php
$curl = curl_init();

curl_setopt_array($curl, array(
    CURLOPT_URL => 'https://api.iapp.co.th/v3/store/ekyc/book-bank',
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_POSTFIELDS => array(
        'file' => new CURLFILE('bankbook.jpg')
    ),
    CURLOPT_HTTPHEADER => array(
        'apikey: YOUR_API_KEY'
    ),
));

$response = curl_exec($curl);
curl_close($curl);
echo $response;
?>

Swift

import Foundation

let url = URL(string: "https://api.iapp.co.th/v3/store/ekyc/book-bank")!
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.addValue("YOUR_API_KEY", forHTTPHeaderField: "apikey")

let boundary = "Boundary-\(UUID().uuidString)"
request.setValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")

var body = Data()
body.append("--\(boundary)\r\n".data(using: .utf8)!)
body.append("Content-Disposition: form-data; name=\"file\"; filename=\"bankbook.jpg\"\r\n".data(using: .utf8)!)
body.append("Content-Type: image/jpeg\r\n\r\n".data(using: .utf8)!)
if let fileData = try? Data(contentsOf: URL(fileURLWithPath: "bankbook.jpg")) {
    body.append(fileData)
}
body.append("\r\n--\(boundary)--\r\n".data(using: .utf8)!)
request.httpBody = body

URLSession.shared.dataTask(with: request) { data, response, error in
    if let data = data {
        print(String(data: data, encoding: .utf8)!)
    }
}.resume()

Kotlin

import okhttp3.*
import okhttp3.MediaType.Companion.toMediaTypeOrNull
import okhttp3.RequestBody.Companion.asRequestBody
import java.io.File

val client = OkHttpClient()
val file = File("bankbook.jpg")

val requestBody = MultipartBody.Builder()
    .setType(MultipartBody.FORM)
    .addFormDataPart("file", file.name, file.asRequestBody("image/jpeg".toMediaTypeOrNull()))
    .build()

val request = Request.Builder()
    .url("https://api.iapp.co.th/v3/store/ekyc/book-bank")
    .addHeader("apikey", "YOUR_API_KEY")
    .post(requestBody)
    .build()

client.newCall(request).execute().use { response ->
    println(response.body?.string())
}

Java

import okhttp3.*;
import java.io.File;

OkHttpClient client = new OkHttpClient();
File file = new File("bankbook.jpg");

RequestBody requestBody = new MultipartBody.Builder()
    .setType(MultipartBody.FORM)
    .addFormDataPart("file", file.getName(),
        RequestBody.create(MediaType.parse("image/jpeg"), file))
    .build();

Request request = new Request.Builder()
    .url("https://api.iapp.co.th/v3/store/ekyc/book-bank")
    .addHeader("apikey", "YOUR_API_KEY")
    .post(requestBody)
    .build();

try (Response response = client.newCall(request).execute()) {
    System.out.println(response.body().string());
}

Dart

import 'package:http/http.dart' as http;

var request = http.MultipartRequest(
    'POST',
    Uri.parse('https://api.iapp.co.th/v3/store/ekyc/book-bank'),
);
request.files.add(await http.MultipartFile.fromPath('file', 'bankbook.jpg'));
request.headers.addAll({'apikey': 'YOUR_API_KEY'});

var response = await request.send();
print(await response.stream.bytesToString());

Limitations

• Thai bank passbooks only; handwritten signature detection only.
• Files larger than 10 MB are rejected; supported formats are JPEG, JPG, and PNG.
• Keep the passbook flat, well lit, and free of glare; tilted or shadowed captures reduce accuracy.

Changelog

Version	Date	Changes
v1.1.1-20260823	23 Aug 2026	Upgraded recognition engine, roughly 3–5 times faster per page (0.2 s median). Field-by-field audit against the previous engine on identical passbooks: 99.45% agreement, with account number, bank name, and account type identical on every book tested; response contract unchanged. Fully self-contained on-premise deployment available.
v2.0	Aug 2022	Added signature detection; overall accuracy improved to 93%.
v1.0	2022	Initial release.