Eliminate errors with automated cheque processing

One of Arya's foremost products was for extraction and verification of cheques (CTS-2010 Standard). For any bank, Cheque clearing is a very important and highly resource intensive process. On any normal day, a leading bank can receive lakhs of cheques for clearance. Being an intricate process, it involves multiple levels of screening and vigilance to ensure regulatory guidelines are met. It was to overcome this challenge that we at Arya developed this product which includes multiple state of the art models to recognise and read handwritten amounts in words and figure, date, payee name, MICR, and account number. All these models work simultaneously to provide speedy results along with confidence scores to assess the performance of the models. While the complete product entails a lot more features, here we've simply exposed the API for the extraction process.

    Cutting-Edge Features    

Why Arya Cheque Processing?

Intelligent Data Localization

Advanced AI algorithms locate and pinpoint key data fields on cheques with precision, minimizing manual intervention

Cheque Format Compatibility

Handles various cheque formats for diverse banking needs

Reduce Operational Costs by 70%

By automating complex extraction, minimize manual work leading to significant cost savings

Adaptive AI Technology

Can continuously learn and improve extraction accuracy, even with complex cheque structures

An AI Platform that you've
always wanted
With more than 80+ APIs, we stand out as the go-to-platform for developers, consistently delivering unparalleled success rates in driving critical decisions.
200 M+

Annual API Volume

95 %+

Accuracy Rate

720 K

Daily API Volume

< 5 Mins

Time to launch

    Effortless AI For Everyone    

More Reasons To Love Arya AI

Hassle-Free,

No Code Platform

Easy to adopt

& integrate

99.99%

API Success Rate

Reliable &

Secure

    Helpful Resources    

Learn More From Our Resources

Blog
Card image cap

6 Dec 2023

Ten Types of Document Fraud to Know in 2024

Financial document fraud has increased in the last two years. Scammers...

Blog
Card image cap

19 March 2024

How to Identify Fake Bank Statements

While we expect bank statements to be accurate records of financial transactions...

Blog
Card image cap

30 April 2024

AI Risk Management in Banking

With banks and financial institutions heavily relying on large volumes of data, they...

Samples to try

Check out the API results using samples provided below.

Drag and drop files

Supports: PDF, JPG, PNG, etc

Drag and drop files

Supports: PDF, JPG, PNG, etc

Please wait...

Uploaded File

JSON
 
Copied

					  
Key Value
{{k|clean|capitalize:true}} :  {{v}}

Documentation

HTTP Method: Post
Endpoint
{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}
Copied
API Token
{{tokenDisplay}}
Copied
API Token UAT
postman wrapper button
{{tokenUDisplay}}
Copied

Usage and Code Samples

curl --location --request POST '{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}' \
--header 'token: < your private token >' \
--header 'content-type: application/json' \
--data-raw '{
	"doc_type":'image',
	"blank_cheque": < flag >,
	"doc_base64": '< base64 string of document >',
	"req_id": '< req id string >'
	     }'
OkHttpClient client = new OkHttpClient().newBuilder().build();
MediaType mediaType = MediaType.parse("application/javascript");
RequestBody body = RequestBody.create(mediaType, "{ "doc_type":'image', "blank_cheque": < flag >, "doc_base64": '< base64 string of document >',"req_id": '< req id string >'  }");
Request request = new Request.Builder()
	.url("{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}")
	.method("POST", body)
	.addHeader("token", "< your private token >")
	.addHeader("content-type", "application/json")
	.build();
Response response = client.newCall(request).execute();
require "uri"
require "net/http"
url = URI("{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}")
https = Net::HTTP.new(url.host, url.port)
https.use_ssl = true
request = Net::HTTP::Post.new(url)
request["token"] = "< your private token >"
request["content-type"] = "application/json"
request.body = "{"doc_type":'image', "blank_cheque": < flag >, "doc_base64": '< base64 string of document >',"req_id": '< req id string >'  }"
response = https.request(request)
puts response.read_body
CURL *curl;
CURLcode res;
curl = curl_easy_init();
if(curl) {
  curl_easy_setopt(curl, CURLOPT_CUSTOMREQUEST, "POST");
  curl_easy_setopt(curl, CURLOPT_URL, "{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}");
  curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
  curl_easy_setopt(curl, CURLOPT_DEFAULT_PROTOCOL, "https");
  struct curl_slist *headers = NULL;
  headers = curl_slist_append(headers, "token: < your private token >");
  headers = curl_slist_append(headers, "content-type: application/json");
  curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
  const char *data = "{"doc_type":'image', "blank_cheque": < flag >, "doc_base64": '< base64 string of document >',"req_id": '< req id string >'  }";
  curl_easy_setopt(curl, CURLOPT_POSTFIELDS, data);
  res = curl_easy_perform(curl);
}
curl_easy_cleanup(curl);
var request = require('request');
var options = {
  'method': 'POST',
  'url': '{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}',
  'headers': {
  'token': '< your private token >',
  'content-type':'application/json'
},
body: '{"doc_type":'image', "blank_cheque": < flag >, "doc_base64": '< base64 string of document >',"req_id": '< req id string >'  }'
};
request(options, function (error, response) {
if (error) throw new Error(error);
  console.log(response.body);
});
var client = new RestClient("{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}");
ṣclient.Timeout = -1;
var request = new RestRequest(Method.POST);
request.AddHeader("token", "< your private token >");
request.AddHeader("content-type", "application/json");
var body = @"{" + "" +
@"    "doc_type": 'image'," + "" +
@"    "blank_cheque": true," + "" +
@"    "doc_base64": '< base64 string of document >'," + "" +
@"    "req_id": < req id string >" + "" +
@"  }";
request.AddParameter("application/json", body,  ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
Console.WriteLine(response.Content);
php
require_once 'HTTP/Request2.php';
$request = new HTTP_Request2();
$request->setUrl('{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}');
$request->setMethod(HTTP_Request2::METHOD_POST);
$request->setConfig(array(
'follow_redirects' => TRUE
));
$request->setHeader(array(
  'token' => '< your private token >',
  'content-type' => 'application/json'
));
$request->setBody('{"doc_type":'image', "blank_cheque": < flag >, "doc_base64": '< base64 string of document >',"req_id": '< req id string >'  }');
try {
  $response = $request->send();
  if ($response->getStatus() == 200) {
  echo $response->getBody();
  }
  else {
  echo 'Unexpected HTTP status: ' . $response->getStatus() . ' ' .
  $response->getReasonPhrase();
  }
}
catch(HTTP_Request2_Exception $e) {
  echo 'Error: ' . $e->getMessage();
}
?>
import requests
url = "{{getEndpoint(url, api_version, pageDetails.ping_endpoint)}}"
payload = {"doc_type":'image', "blank_cheque": < flag >, "doc_base64": '< base64 string of document >',"req_id": '< req id string >'  }
headers = {
  'token': '< your private token >',
  'content-type':'application/json'
}
response = requests.request("POST", url, json=payload, headers=headers)
print(response.text)

Request Parameters

Header parameters
Name Description
token String
Body parameters
Name Description
body {
  "req_id" : < string >,
  "doc_base64": < base64 encoded string >
  "doc_type" : < string>,
  "blank_cheque" : < boolean>,
}

Response Parameters

Status: 200 - API Request Successful
Body parameters
Name Description
body {
  "req_id" : < string >,
  "success" : < boolean >,
  "error_message" : < string >,
  "result" : < dict >,
}

Field Details

Request Field Details
Fields Values/Description
doc_type “image”
req_id Unique request ID used for processing requests
doc_base64 Base64 encoded string of the document
blank_cheque Boolean
Response Field Details
Fields Values/Description
req_id Corresponding request id
success Flag if the request is processed successfully
error_message If success is False then: Error message
result Extracted data dictionary