There's been plenty of news surrounding Microsoft Azure in recent days. Cross-Azure IoT collaboration with IoT Messaging has been unveiled, there are new cloud regions in Switzerland, and open-source machine learning framework PyTorch's version 1.2 is now fully supported on Azure.
Earlier this year, Microsoft announced new AI and machine learning (ML) offerings as part of Azure Cognitive Services. Among these was Form Recognizer, an AI-powered document extraction utility which applies advanced ML algorithms to extract relevant data from forms.
Today, the tech giant has revealed that in addition to recognition for printed documents, support has now been expanded to handwritten and mixed-mode forms as well. The latter implies that even a mix of printed and handwritten values can be extracted from a document.
The new capability is available in preview and its usage is supported with various types of documents. Among others, these include medical, financial, insurance, and manufacturing forms. Optical character recognition (OCR) technology has been utilized to expand the scope of the service. Microsoft believes that the addition of the new feature has opened up several new opportunities for users, allowing them to:
- Expand your available data set: If you are only extracting data from machine printed forms, expand your total data set to mixed-mode forms and historic handwritten forms.
- Create one application for a mix of documents: If you use a mix of handwritten and printed forms, you can create one application that applies across all your data.
- Avoid manual digitization of handwritten forms: Original forms may be fed to Form Recognizer without any pre-processing, extracting the same key-value pairs and table data you would get from a machine-printed form to reduce costs, errors, and time.
You can learn more about Forms Recognizer through its documentation or the website. If you are interested, you can then request Microsoft for access to the service, since it is currently only available in limited preview.