Tag Image Action In Microsoft Computer Vision Cognitive Service With Desktop Flow Using Microsoft Power Automate

Microsoft Power Automate, is a software by Microsoft for automation of recurring tasks. It is part of the Microsoft Power Platform line of products together with products such as Power Apps and Power BI. More Details here.

Microsoft cognitive services enables users to accelerate decision-making using artificial intelligence without requiring machine learning expertise.

Desktop flows are the existing robotic process automation (RPA) capabilities in Power Automate and enable to automate all repetitive desktop processes. It also provide a wide variety of Microsoft cognitive actions that allow you to integrate this functionality into your flows. Text analysis, computer vision, and spell checking are all tasks that Microsoft cognitive actions can perform. More Details here.

The Microsoft cognitive computer vision - Tag image action generates a list of words, or tags, that are relevant to the content of the supplied image. The Computer Vision API can return tags based on objects, living beings, scenery or actions found in images.

Reading this article, you can learn how to extract text with Microsoft cognitive computer vision - Tag image action in Desktop flow using Microsoft Power Automate.

The following important tools are required for developing Microsoft Power Automate,

1. Windows 10/11 (Recommended)
2. Power Automate Desktop - Download the Power Automate installer
3. Microsoft Azure account - https://azure.microsoft.com/en-in/

Now we can discuss step by step App development.

Step 1

Open Microsoft Power Automate -> New Flow

Next, Give the Flow name as PADCogTagImg, Click the Create button,

After that, we are able to see the Desktop flow,

Step 2

For Testing Microsoft cognitive computer vision - Tag image action,

First, Get the Azure cognitive service Subscription details - Refer the link for creating a Coginitive service in Microsoft Azure.

The Sample Image, Image file is,

Next, Add the Tag image action, Set the Server location Parameter as West US 2, Subscription key Parameter as ************** and Provide image Parameter as From file, Image file Parameter as C:\Users\shanv\Desktop\Sample Img.jpg, Variable Produced Parameter as %JSONResponse% and Click Save Button

For Displaying Result, Add the Display message action and Set the Message box Title Parameter as Display Tag Image Result, Message to display Parameter as %JSONResponse% Click Save Button

Now, Save the PADCogTagImg Desktop Flow,

Step 3

Now we can run your PADCogTagImg Desktop Flow in Microsoft Power Automate,and the output of the PADCogTagImg is,

Summary

Now you have successfully tested Microsoft cognitive computer vision - OCR action in Desktop flow - PADCogTagImg in Microsoft Power Automate.