Hello to all friends of Document Understanding!
The moment many of you have been waiting for is here. Handwriting support has come to the proprietary UiPath Document OCR engine. This is available right now only in Cloud, at the standard endpoint https://du.uipath.com/ocr For endpoints on various other Regions supported, please see the documentation page here. It will come, on premises with the 2022.4 On Premises release.
This release brings English handwriting recognition capabilities to the entire Document Understanding framework. Previously this was confined only to the Intelligent Form Extractor component, but now you can also build Forms AI models, Machine Learning Extractor models which can read handwriting, or even document classifiers using Keyword, Intelligent Keyword or Machine Learning Classifiers.
There is no change in the licensing or pricing. UiPath Document OCR remains free to use with no restrictions for all customers with Enterprise license of Document Understanding product. Customers with Community licenses can still use it with some limitations.
Intelligent Form Extractor (IFE) will be deprecated at some point (announced here), so it is recommended that you start using Form Extractor (FE) in any newly developed workflows from now on. Of course the IFE will remain under the standard Support schedule, but the handwriting capability will no longer be updated as we focus our efforts on the unified Document OCR which reads both print and handwriting.
For the latest and greatest capabilities in Document OCR and Handwriting recognition going forward, make sure to use Form Extractor with UiPath Document OCR.
Happy automating!
Your friendly Document Understanding team.