New Feature Release: OCR Only Schema

With this blog post we want to announce that Document Information Extraction has new features, as of november 9th, 2022, one of which is OCR-only Schema. Stay here to read more about this feature or jump to this blogpost to find out more about the further features of this feature release.

OCR-only Schema

The new feature OCR-only Schema is here to serve users who wish to get the OCR output only, from Document Information Extraction, and as quickly as possible. To enable that, we now provide the pre-defined schema (SAP_OCROnly_schema). This allows users to request the OCR output.

 Best parts about this feature:

  • Use cases where only the OCR-output is required are supported, e.g. for further custom processing in the target application.
  • Take advantage of SAP’s OCR features such as deskewing, derotation, or handwriting.
  • Benefit of a faster document processing time.

In which context could this be useful?

Only having the text as an output can be very helpful when using Business Entity Recognition. Due to the fact that Business Entity Recognition requires plain and unstructured text as input, the OCR-only Schema can be used to extract only the text from different types of documents in order to then have the right input.

Let’s also take a look on another use case, shown in this short demo.

In the first step you select the right schema: OCR_Only Schema.

As a second step you upload your file which has to be extracted. In this situation it is a photo of a container ID:

You can see here the OCR function of Document Information Extraction. What the demo shows, is the extraction of a container ID from a photo. The service extracts the ID and then shows only the extracted content, without putting it into a table, as it usually does. One can now use the output for further processing.

Take a short look on the custom schemas:


Learn more

Read more about the news of Document Information Extraction on the help portal!

What is Document Information Extraction?

Document Information Extraction is one of the SAP AI Business Services on the SAP Business Technology Platform (SAP BTP). This ML-enabled service is available through the Cloud Platform Enterprise Agreement (CPEA) and also in the Pay-As-You-Go (PAYGO) model.

Tutorials & Learnings

Blog posts:

SAP Community Page: