📗✍️ Thai Bank Book OCR with Signature Detection

📗✍️ ระบบอ่านสมุดบัญชีธนาคารพร้อมตรวจจับลายเซ็น

Welcome to Bank Book OCR with Signature Detection API, an AI product developed by iApp Technology Co., Ltd. Our API is designed to extract information from bank books and detect signatures with high accuracy and speed.

Getting Started

Prerequisites
- An API key from iApp Technology
- Bank book images
- Supported formats: JPEG, JPG, PNG
- Maximum file size: 2MB
Quick Start
- Fast processing time
- High accuracy text recognition
- Support for multiple file formats
- Signature detection capability
Key Features
- Bank book information extraction
- Signature detection and verification
- Multiple bank support
- High accuracy recognition
Security & Compliance
- GDPR and PDPA compliant
- No data retention after processing

How to get API Key?

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

Features and Capabilities

Core Features

The Bank Book OCR API provides robust capabilities to extract and recognize key information from bank book images. Below is an overview of its features:

Core Capabilities

Bank Name Recognition: Extracts the full name of the bank, including abbreviation and code.
Account Number Recognition: Detects and accurately extracts the bank account number.
Account Name Recognition: Retrieves the name of the account holder.
Bank Branch Recognition: Identifies the branch name associated with the bank account.
Signature Detection: Recognizes the presence of a signature on the document.
Confidence Scoring: Provides a confidence level percentage for each recognized field.

Supported Banks

The API supports multiple popular banks in Thailand:

SCB (Siam Commercial Bank)
Bangkok Bank
Krungthai Bank
Kasikorn Bank
Krungsri Bank (Bank of Ayudhya)
TMB Bank

Example

Request:

Image Preview Bank Book with Signature OCR Example

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

Response:

{
  "bank_book_results": {
    "accountType": "null",
    "account_name": "XXXXX XXXXXXXคุณ",
    "account_number": "90XXXXXX61",
    "bank_branch": "มหาวิทยาลัยธรรมศาสตร์ ท่าพระจันทร์",
    "bank_name": "กรุงเทพ (BBL)",
    "file_name_bookbank": "1376070230-image3-o"
  },
  "confidence": "64.43",
  "inference_time(s)": "0.478",
  "message": "Success",
  "reason_codes": {
    "accountType": { "code": 1, "message": "Success" },
    "account_name": { "code": 1, "message": "Success" },
    "account_number": { "code": 1, "message": "Success" },
    "bank_branch": { "code": 1, "message": "Success" },
    "bank_name": { "code": 1, "message": "Success" },
    "file_name_bookbank": { "code": 1, "message": "Success" },
    "signature": { "code": 1, "message": "Success" }
  },
  "signature": "Detected",
  "status": 200
}

API Reference

Endpoint

POST https://api.iapp.co.th/book-bank-ocr/file

Request Parameters

Headers

Key	Required	Description
apikey	Yes	Your API key for authentication.

Body (Form-Data)

Key	Type	Required	Description
file	File	Yes	The file to be uploaded for OCR. Ensure the file path is specified correctly.

Response Parameters

Main Response Object

Key	Type	Description
`bank_book_results`	Object	Contains the extracted data from the bank book.
`confidence`	String	Confidence level of the OCR result, expressed as a percentage.
`inference_time(s)`	String	Time taken to process the OCR request, in seconds.
`message`	String	Status message of the request (e.g., "Success").
`reason_codes`	Object	Detailed reason codes for each extracted field.
`signature`	String	Status of signature detection (e.g., "Detected").
`status`	Integer	HTTP status code of the response (e.g., 200 for success).

Book Bank Result Object

Key	Type	Description
`accountType`	String	Type of bank account (e.g., "Savings" or "null" if unknown).
`account_name`	String	Name of the account holder.
`account_number`	String	Account number of the bank account.
`bank_branch`	String	Name of the bank branch.
`bank_name`	String	Full name of the bank, including the abbreviation and code.
`file_name_bookbank`	String	File name of the uploaded bank book.

Reason Codes Object

Each field in the bank_book_results object has an associated reason code indicating success or failure.

Field	Key	Type	Description
Account Type	`accountType`	Object	Code and message for account type.
Account Name	`account_name`	Object	Code and message for account name.
Account Number	`account_number`	Object	Code and message for account number.
Bank Branch	`bank_branch`	Object	Code and message for bank branch.
Bank Name	`bank_name`	Object	Code and message for bank name.
File Name	`file_name_bookbank`	Object	Code and message for the file name.
Signature	`signature`	Object	Code and message for signature detection.

API Error Message

Reason Codes

Status Code	Status Message	Description
1	pass	Confident about the content read
0	manual check	Not confident about the content read, pending manual check

Signature Reason Codes

Status Code	Status Message
1	no signature detected
2	shade/background
3	multiple pic detected
4	other (unspecified)

Common API Error Messages

Status Code	Status Message	Description
404	REQUESTED_URL_NOT_FOUND	API Route not found in request
413	FILE_IS_TOO_LARGE: (more than 2 MB)	The file size is too large
416	METHOD_NOT_ALLOWED	Method name (GET, POST) in the URL is incorrect.
427	LONG_TIME_TO_PROCESS	The server is processed for a long time.
428	LONG_TIME_TO_REQUEST	The client is waiting in the queue for a long time.
461	NO_FILE_ATTACHED	No file attached.
462	ATTACH_ONE_IMAGE_AT_A_TIME	Multiple input images
560	SERVER_IS_BUSY: (Please try again in a few seconds.)	Server is working on many requests.

Code Example

Python

import requests

url = "https://api.iapp.co.th/book-bank-ocr/file"

payload = {}
files=[
  ('file',('{YOUR UPLOADED FILE}',open('{YOUR UPLOADED FILE}','rb'),'image/jpeg'))
]
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}"))

let config = {
    method: "post",
    maxBodyLength: Infinity,
    url: "https://api.iapp.co.th/book-bank-ocr/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/book-bank-ocr/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}')),
  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}",
    "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/book-bank-ocr/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}",
    File("{YOUR UPLOADED FILE}").asRequestBody("application/octet-stream".toMediaType()))
  .build()
val request = Request.Builder()
  .url("https://api.iapp.co.th/book-bank-ocr/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}",
    RequestBody.create(MediaType.parse("application/octet-stream"),
    new File("{YOUR UPLOADED FILE}")))
  .build();
Request request = new Request.Builder()
  .url("https://api.iapp.co.th/book-bank-ocr/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/book-bank-ocr/file'));
request.files.add(await http.MultipartFile.fromPath('file', '{YOUR UPLOADED FILE}'));
request.headers.addAll(headers);

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

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

History

Version 1.2

Expected to be released by the end of May

Increase accuracy
Bank branch recognition
Account name recognition

Version 1.1

Released on 20th April 2022

Overall Accuracy = 78%

Increased accuracy:
Account number recognition by 8% (old version: 88.84%, new version: 96.82%)
Bank name recognition by 4% (old version: 94.87%, new version: 99.5%)

Version 1.0

Released on 24th March 2022
Overall Accuracy = 74.85%

First initial version
Supported Banks: SCB, Bangkok Bank, Krungthai Bank, Kasikorn bank, krungsri bank(Bank of Ayudhya), TMB Bank
Supported fields: Bank name, Account number, Account name, Bank branch

Pricing

AI API Service Name	IC Per Request	On-Premise
Book Bank OCR with Signature Detection	1.25 IC/Request	Contact

Getting Started​

Features and Capabilities​

Core Features​

Core Capabilities​

Supported Banks​

Example​

Request:​

Response:​

API Reference​

Endpoint​

Request Parameters​

Headers​

Body (Form-Data)​

Response Parameters​

Main Response Object​

Book Bank Result Object​

Reason Codes Object​

API Error Message​

Reason Codes​

Signature Reason Codes​

Common API Error Messages​

Code Example​

Python​

JavaScript​

PHP​

Swift​

Kotlin​

Java​

Dart​

History​

Version 1.2​

Version 1.1​

Version 1.0​

Pricing​