Azure Computer Vision - Optical character recognition

Use the Azure Computer Vision - Optical character recognition action A tool for building the processes, logic, and direction within workflows. Actions are the steps the workflow performs to complete a process. to extract printed or handwritten text from images. You can extract text from images, such as photos of license plates or containers with serial numbers, as well as from documents - invoices, bills, financial reports, articles, and more.

Input requirements:

  • Supported image formats: JPEG, PNG, GIF, BMP.

  • Image file size must be less than 4MB.

  • Image dimensions must be at least 50 x 50.

For more information about the Azure Computer Vision connector, go to Azure Computer Vision.

Before you begin: 

Jump to:

Configure the Azure Computer Vision - Optical character recognition action

  1. Add the action to the workflow and open the action configuration panel. For more information, see Add an action to the workflow.

  2. Select a Connection. If you do not have a connection, see Add a connection.
  1. Insert a variable that contains the Image file to describe.

Azure Computer Vision - Optical character recognition action fields and settings

Section Field Description Variable types

(unlabeled)

Connection Credentials and other settings that enables workflows to communicate with external systems, services, or applications. It's required to pass data between the workflow and the indicated service, which could be a cloud service, business application, or content store.

The Azure Computer Vision connection used to access the account for which you want to Optical character recognition.

To refresh the available connections, click .

 (n/a)

 

 Image

The variable containing the image file to be analyzed.

Note: Your tenancy's default file storage location must be configured to hold files for later reference by the workflow. This location is used for uploaded files and for files stored as output from actions.

File
  Language The language of the text in the image that you need transcribed using the optical character recognition service. Text, Decimal, Integer, Boolean, DateTime, Collection
Output Optical character recognition results

Stores the result of the action as an object with the following variables:

  • Language: (Text) The BCP-47 language code of the text detected in the image.

  • Orientation: (Text) The angle of the text within the image. The value (up, down, left, or right) refers to the direction that the top of the recognized text is facing, after the image has been rotated around its center according to the detected text angle.

  • Regions: (Collection) An list of objects, where each object represents a region of recognized text. A region consists of multiple lines (e.g. a column of text in a multi-column document).

    • Bounding box: (Text) Bounding box of a recognized region. The four integers represent the x-coordinate of the left edge, the y-coordinate of the top edge, width, and height of the bounding box, in the coordinate system of the input image.

    • Lines: (Collection) A list of objects, where each object represents a line of recognized text.

      • Bounding box: (Text) Bounding box of a recognized line. The four integers represent the x-coordinate of the left edge, the y-coordinate of the top edge, width, and height of the bounding box, in the coordinate system of the input image.

      • Words: (Collection) A list of objects, where each object represents a recognized word.

        • Properties: (Text) The properties of the recognized text.

        • Text: (Text) The words recognized in this portion of the image.

    • Text angle: (Decimal) The angle, in radians, of the detected text with respect to the closest horizontal or vertical direction. After rotating the input image clockwise by this angle, the recognized text lines become horizontal or vertical.

 Object