Bank Statement OCR

 

This article walks you through the building process of an OCR API that extracts data from Bank Statements using our deep learning engine. It will work for any bank company or bank statement template. 

 

 

Prerequisites

1. You’ll need a free account. Sign up and confirm your email to login.
2. You’ll need at least 20 Bank Statement images or pdfs to train your OCR.

 

 

Define your Bank Statement use case

 

First, we’re going to define what fields we want to extract from your Bank Statement. 

 

 

 

• Full name: The full name of the client 

 

• Address: The address of the client  

 

• Account Number: The account number 

 

• Opening Balance: The opening balance of the account at the beginning of the month 

 

• Closing Balance: The closing balance of the account at the end of the month

 

 

That’s it for our use case. Feel free to add any other relevant data to fit your requirements.

 

 

Deploy your API

 

Once you have defined the list of fields you want to extract, head over to the platform and press the ‘Create a new API’ button.

 

You land now on the setup page. Here is the image you can use for setting up the API, and my setup looks like this:

 

 

 

Once you’re ready, click on the “next” button. We are going to specify the data types for each of the fields we want our API to extract.

 

 

To go further, you can download this json config to set up your data model or do it manually.

 

Full name: type String that never contains numeric characters.

 

 

 

 

Address: type String without specifications. 

 

 

Account Number: type String with no alpha characters.

 

 

Opening Balance: type Number without specifications. 

 

 

Closing Balance: type Number without specifications. 

 

 

 

Once you’re done setting up your data model, press the Start training your model button at the bottom of the screen.

 

 

 

Train your Bank Statement OCR

 

 

 

 

You’re all set! 

 

Now is the time to train your Bank Statement deep learning model in the Training section of our API. 

 

In a few hours (minutes if you're fast), you’ll get your first model trained and will be able to use your custom OCR API for parsing Bank statements in your application.

 

To get more information about the training phase, please refer to the Getting Started tutorial. If you have any questions regarding your use case, feel free to reach out on our chat!