What is cognitive data capture?

Cognitive data capture uses artificial intelligence (AI) to mimic the way the human mind reads structured documents. This approach has two key features: the AI learns to recognize information through exposure to examples rather than manual configuration by experts, and it can recognize a lot of information in documents with layouts it hasn’t seen before.

Contrary to manual data entry or traditional OCR, cognitive data capture does not require extra manpower. It also saves you the hassle, time, and cost of setting up endless rules and templates (you can read detailed comparisons of effort in our TCO analysis series).

Rossum’s cognitive data capture AI uses deep neural networks to recognize patterns in documents like a human mind would. This enables the platform to understand the underlying general structure of business documents like invoices. Rossum’s unique neural network architecture allows it to comprehend a vast range of layouts; it also ensures highly accurate data extraction.

Refer to our founders’ blog series on cognitive data capture for an in-depth look at the technical difference between legacy OCR solutions and cognitive data capture, and how Rossum’s technology works.

Can Rossum be implemented on-premises?

To ensure up-to-date and widely scalable security, maintenance, and regular updates, we do not offer on-premises solutions. The cloud is the most reliable medium through which we can deliver a widely scalable service with the highest level of security. It is worth noting that cloud-based solutions deliver security benefits that are comparable to those of on-premises solutions. 

Where are your servers located?

Rossum runs on AWS out of Ireland. Enterprise customers can have Rossum deployed on AWS cloud data storage in a different country.

What languages does Rossum recognize?

Most languages using a variation of the latin script are supported out of the box. The most popular languages processed by Rossum customers are English, French, German, Nordic languages (Danish, Norwegian, Swedish, Finnish), Spanish, Italian, Czech, Slovak, Polish, Hungarian and Romanian.

What is the price for an annual subscription?

Before we can give you a price estimate, we need to understand your requirements. In addition to your estimated annual document volume, we need to know other information, including which data fields you want to extract and any customization and/or training requirements.

If you are interested in a getting a quote from us, please fill in and send us this form, and one of our experts will get back to you promptly.

How can I integrate Rossum into my ERP or document management system?

As our main scope is on data extraction, we do not provide integration services directly. We have extensive API documentation that facilitates smooth integration with most business systems. Read about the API.

You can also check out this guide, which features examples of three different types of Rossum integration, including manual integration. We’ve also posted an example of UiPath integration.

For smaller edits that you need to make to ensure your integration works properly, such as adjusting the format of the output file, we can develop a custom connector for you.

How does Rossum handle fields that differ in format among countries and languages, such as dates or decimals?

The data capture engine can handle any format and normalize it according to your preferred standardized representation. To deal with genuinely ambiguous cases, we have a special “locale” setting that enables you to adjust the platform to handle individual document queues according to region of origin. Date formats are very flexible, and we can customize your UI so it displays exported data in the format you wish it to be in.

You can find some of the supported formats here, under the “Date format” section; the tokens mentioned there are available at this link.

Is Rossum GDPR-compliant?

We are fully committed to ensuring compliance with GDPR. We process documents provided by customers for the primary purpose of data capture, based on the instructions of our customers, and for the secondary purpose of further research and development of data extraction technology. Based on the nature of the data and the GDPR balance test, we have full reason to believe that this processing is fully compliant with GDPR, particularly when not concerning third-party consumer invoices or invoices with sensitive personal data. You can read more about this in our terms and conditions

How does Rossum maintain secure code integrity?

We follow the OWASP Secure Coding Practices and rely on the extensive experience of our senior team members. In the event of a code change, we perform design reviews, code reviews, and security reviews. Every commit is inspected and reviewed by at least one other software engineer. We use thorough automated testing, including unit tests and integration tests, as well as manual testing to ensure code quality and security. We also use automated third-party tools for static source code checks and vulnerability scanning. Our platform  undergoes regular penetration testing by an independent third party.

How does Rossum encrypt data?

We always use encryption when transferring data in and out of the cluster. We use AES 256 keys managed in AWS Key Management Service for data at rest and TLS v1.2 for all data in transit using HTTPS (including HSTS).

All outside communication is strictly encrypted when in motion, typically via HTTPS for regular production operation. For some service and maintenance purposes, we use SSH encryption to encrypt external communication.

Communication with the database is always encrypted. We use an audit log for all operations that are executed in the application.

What other types of document does Rossum support?

In addition to invoices, Rossum can extract data from other semi-structured documents including receipts, purchase orders, and shipping documents. We can also train a custom AI model to capture data from specific types of document, so you can use Rossum to process non-invoice documents.

Our custom training add-on has the capability to capture data from any document defined, at least in part, by its layout. Prime examples of such documents include invoices, bills, and receipts. Rossum can also process documents with similar formats, such as purchase orders, delivery notes, confirmations, statements, and forms.

For Rossum to successfully capture data from any document, two conditions apply:

  1. content must be in Latin characters
  2. tables must be in a grid format and their columns must have uniform meaning


Automate data extraction from your documents with Artificial Intelligence.
Free trial