Skip to Content
Product Information
Author's profile photo Maria Goepfert

Scene Text Recognition with Document Information Extraction

We are happy to announce a new feature available in Document Information Extraction as of April  5th, 2023.

Document Information Extraction

Document Information Extraction is one of the services offered by the SAP AI Business Services portfolio. It is available through the Cloud Platform Enterprise Agreement (CPEA) and also in the Pay-As-You-Go (PAYGO) model. It enables its users to extract information from various types of business documents, for example, invoices, purchase orders, and payment advices using pre-trained AI models. This blog presents you another important capability of Document Information Extraction which can support its users to work efficiently.

Scene Text Recognition Feature of Document Information Extraction

Document Information Extraction is able to process standard documents like invoices, purchase orders and others, directly out of the box. But not every business process starts and ends within offices, processing business documents. The supply chains are very diverse, bringing workers and therefore also important information to different locations. From warehouses, to productions, to platforms in the sea.

No matter in which location, employees are facing a lot manual work when it comes to converting data from being printed somewhere (on palettes, on seals, on containers, on documents, etc.) to a digitized format, preparing it for further processing. Important enterprise data is locked within unstructured formats, like simple PDFs, but also in scene text. The process of structuring the data can get very cumbersome, time consuming and oftentimes quite error prone.

The new capability of Document Information Extraction, scene text recognition, enables users to extract important written information outside of standard documents.

How does this work?

As simple as taking a photo and sending it via the API to Document Information Extraction. After the processing of the photo, you will be able to download the output and process it further!

Example Use Case

For a better understanding of the usefulness of this capability, let’s take a look on an example of a use case, in which Document Information Extraction can be implemented.

The following scenario is situated within the oil and gas industry. Some employees are working on oil or gas platforms on the sea and are required to process a lot of data under time pressure. This oftentimes happens in severe weather conditions, wearing gloves and other safety attires. Employees have hand-held devices and need to manually type the IDs and seal numbers from the incoming and outgoing containers into their devices. This documentation is a crucial part in the logistic and supply chain process, being oftentimes very error prone when done manually.

Using Document Information Extraction, workers can simply take photos of the numbers and IDs of the containers and upload them in an according application, where Document Information Extraction can then take care of the extraction and enrichment. After the user uploads the file with the needed information, the Optical Character Recognition (OCR) function of Document Information Extraction extracts all the important information which can be validated quickly by the user. All the extracted data can then be populated in to the UI automatically for further processing.

Find more information about the OCR feature on the SAP Help Portal page for Document Information Extraction.

Using Document Information Extraction in such a scenario helps customers to speed up the processing of big volumes or hard to handle data, and at the same time ensuring the high accuracy and precision of the extracted information. Document Information Extraction uses a machine learning model here, which is pre-trained and therefore can be used as a plug and play feature in order to achieve immediate productivity. Due to high efficiency and automation of the process, customers are also able to reduce business document processing costs.


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:

Assigned Tags

      1 Comment
      You must be Logged on to comment or reply to a post.
      Author's profile photo Rocky Sharma
      Rocky Sharma

      Hi Maria,

       

      Can this also read a picture which is handwritten containing numbers or texts?

       

      Thanks,

      Rocky