**YouTube** is an American [online video-sharing](https://en.wikipedia.org/wiki/Video_hosting_service "Video hosting service") [platform](https://en.wikipedia.org/wiki/Web_platform "Web platform") headquartered in [San Bruno, California](https://en.wikipedia.org/wiki/San_Bruno,_California "San Bruno, California")

cf3f59da-c081-4fab-99d2-f02e60e183b0.PNG

Update: Microsoft released a new version: Form Recognizer V2, which can be found here:

[https://connect.uipath.com/marketplace/components/microsoft-azure-form-recognizer-v2](https://connect.uipath.com/marketplace/components/microsoft-azure-form-recognizer-v2)

  

Note: This activity pack is NOT deprecated in favor of the updated Form Recognizer v2, as both versions of the service still exist. Version 2 offers however multiple improvements.

  

Azure Form Recognizer is a document understanding service offered by Microsoft. Extract text, key/value pairs and tables from documents, forms and receipts, without manual labeling by document type. Uses pre-built and unsupervised learning components to understand the layout and relationships between fields and entries in documents, pulling information in an organised manner. Uses a predefined ML model for receipt analysis and allows training custom models for form analysis.

Form Recognizer provides:

*   **Key-value pair extraction** - Form Recognizer extracts key-value pairs in document images automatically so that you can retain the inherent context of the document without any manual intervention. This makes it easy to import the extracted data into a database, or to provide it as a variable into an application.
*   **Table extraction** \- Form Recognizer preserves the composition of data stored in tables during extraction. This is helpful for documents that are largely composed of structured data, such as financial reports or medical records that have column names in the top row of the table followed by rows of individual entries
*   **Bounding boxes** - All extracted data is returned with bounding box coordinates. The coordinates make up a polygon frame that encompasses each piece of identified data, such as a single word, a line, or a table. This is helpful for being able to audit where a word or number came from in the source document. It also helps to guide the user in document search systems that return scans of original documents as the search result.

The Form Recognizer activities allow you get a list of your models, or get, delete or train a specific model. It also allows you to analyze forms or receipts. This package includes the following activities:

**Authentication**

*   Form Recognizer Scope

**Analyze**

*   Analyze Form
*   Analyze Receipt

**Manage Model**

*   Get Models
*   Get Model
*   Get Model Keys
*   Delete Model
*   Train Model

**Documentation**

Click these links for [information](https://docs.uipath.com/integrations/docs/microsoft-azure-form-recognizer-about), [setup](https://docs.uipath.com/integrations/docs/microsoft-azure-form-recognizer-setup), and [technical references](https://docs.uipath.com/integrations/docs/microsoft-azure-form-recognizer-technical-references).

A set of activities that enables the integration with Microsoft Azure Form Recognizer service