Invoice OCR

Enhance the effectiveness of your organisation with Optical Character Recognition and machine learning. Process invoices automatically and securely with Klippa.

Trusted by more than 1000 brands worldwide

Also looking for a solid partner? Give us a ring at +31 50 2111631

What we can do with invoices

Our machine learning technology can automate many invoices related business processes via our APIs and SDKs.
Invoice scanning
Invoice format and quality conversions
Invoice to text, UBL, CSV, XSLX or JSON with OCR
Data extraction on invoices
Classifying invoices and invoice line items
(Cross)Validating invoice data
Invoice management
Workflow optimisation

Invoice data extraction

An image speaks more than a thousand words. Below is an example of the three steps our OCR engine takes to automatically extract data from invoices.

Uploading invoices to the API

The first step is providing a picture or a PDF file of an invoice to our API. Usually this is done from a mobile app, email, FTP or web application.

The document can be send cropped or uncropped (with some kind of background). If it is send uncropped, the Klippa API will automatically crop the document.

The Klippa invoice scanning SDK can also be used to implement in mobile apps. 

Image to text using OCR

As soon as an invoice picture or PDF has been received, it is converted to a TXT file. In this step all the text from the document is extracted, but it is not yet structured.

Getting JSON output from the API

The Klippa Parser takes the TXT gained from the OCR in step 2 and converts it into structured JSON using machine learning. The JSON is then returned as output from the API. From here the invoice can easily be processed into your database. Wether you are processing invoices for accounting or loyalty purposes, Klippa is here to help.

The image on the left is a simplified example of the JSON response.
Reduce cost
Spend less on processing invoices by using Klippa.
Improve speed
Process invoices automatically within seconds. Perfect for accounting, accounts payable automation, cashbacks and loyalty.
Reduce errors
Prevent manual data entry errors with high quality data extraction on invoices.
Prevent fraud
Automatically recognise errors, duplicates and fraud.
What invoice fields are extracted?
Below the default extracted data fields (checkmarks) and automated checks (locks) are listed. These can be customised for each customer. On request additional fields can also be extracted.
Document type
Image quality
Country of origin
Invoice language
Merchant name
Merchant address details
Merchant contact details
Merchant website
Client details
Payment method
Card number
Amount of change
Date of purchase
Due date
Date of delivery
Total amount
VAT amounts
VAT percentages
Line item descriptions, quantity, prices and category
Invoice number
Purchase order number
Chamber of commerce number
VAT number
And many more fields
Find duplicates via image hashing
Identify fraudulent documents via crosschecks
Let's talk over the phone!
We love to explain more about Klippa via a short phone call. If you want us to call you back, just choose a date and time that suits you best. If you leave the date and time empty we will call you within 30 minutes!
We are available for calls in English, Spanish, German and Dutch during office hours (CEST timezone). You can reach us at +31 50 2111631.

Frequently Asked Questions

What does invoice OCR cost?
The pricing structure for Klippa invoice capturing depends on the amount of fields and the document volume. Both pay per use and monthly licenses are available. Get in contact with our solution architects to get an exact quote.
What types of invoices are supported?
Klippa can extract data from parking receipts, fuel receipts, payment receipts, grocery store receipts and receipts from all other types stores.
Are invoice line items extracted?
Klippa definitely supports line item extraction on invoices. We have a special machine learning algorithm focussed on line item extraction. For every line the quantity, description, price per unit, total price and potentially VAT values are extracted. Optionally SKU, weights and sizes can also be extracted. 

After the line item OCR extraction Klippa also performs line item classification. Using an additional algorithm we classify over 20 categories for each line. For example ‘Food’, ‘Electronics’, ‘Alcoholic’ and many more options. Based on these categories the VAT deductibility can be determined, loyalty points can be distributed and general ledger accounts can be suggested. This is perfect to implement as a solution for accounts payable automation.
What use cases are supported?
Klippa tries to extract as much data as possible from invoices via OCR and machine learning. This ensures that we can support as many use cases as possible. 

Use cases we come across often are quality detection, validity verification, warranty insights, invoice analytics, spending insights, cashbacks, loyalty, VAT reclaim, 2 way matching, 3 way matching and accounting. 

RPA accounts payable automation is currently the most popular use case. With Klippa you can automate up to 95% of your invoice processing using OCR and machine learning. 
What languages does Klippa support?
All European languages are supported. Our engine performs best on receipts in Dutch, Norwegian, Danish, Swedish, Finnish, Italian, Portuguese, English, Spanish, German, Hebrew or French. Other languages can be supported on request by training our machine learning models.
Is Klippa invoice capturing GDPR compliant?
All the services that Klippa offers are fully GDPR compliant. We only use ISO certified servers within the European Union for processing invoices. A data processor agreement is in place. We do not store any of your or your customers data after processing.
Is there documentation for the invoice OCR API?
Klippa was founded by developers. Therefore we understand the value of a well documented API. Our documentation is created using SWAGGER and can be found via this link.

 Schedule a free online demonstration

Get a clear view of how Klippa can help automate your invoice processing. A demo takes just 30 minutes.

Please feel free to ask all your questions.
 Get in touch by mail, phone or chat!
+31 50 2111631