azure-ai-services

Azure AI Services

Azure AI—a portfolio of artificial intelligence (AI) services designed for developers and data scientists—to do more with less. Take advantage of the decades of breakthrough research, responsible AI practices, and flexibility that Azure AI offers to build and deploy your own AI solutions. Access high-quality vision, speech, language, and decision-making AI models through simple API calls, and create your own machine learning models using an AI supercomputing infrastructure, familiar tools.

Azure AI services help developers and organizations rapidly create intelligent, cutting-edge, market-ready, and responsible applications with out-of-the-box and pre-built and customizable APIs and models. Example applications include natural language processing for conversations, search, monitoring, translation, speech, vision, and decision-making.

Most Azure AI services are available through REST APIs and client library SDKs in popular development languages. For more information, see each service’s documentation.

Select a service from the table below and learn how it can help you meet your development goals.

Service Description
 Anomaly Detector  (retired) Identify potential problems early on
 Azure Cognitive Search Bring AI-powered cloud search to your mobile and web apps
Azure OpenAI Perform a wide variety of natural language tasks
Bot Service Create bots and connect them across channels
Content Moderator (retired) Detect potentially offensive or unwanted content
 Content Safety An AI service that detects unwanted contents
 Custom Vision Customize image recognition to fit your business
 Document Intelligence Turn documents into usable data at a fraction of the time and cost
Face Detect and identify people and emotions in images
 Immersive Reader Help users read and comprehend text
Language Build apps with industry-leading natural language understanding capabilities
Language understanding (retired) Understand natural language in your apps
Metrics Advisor (retired) An AI service that detects unwanted contents
 Personalizer (retired) Create rich, personalized experiences for each user
QnA maker (retired) Distill information into easy-to-navigate questions and answers
Speech Speech to text, text to speech, translation and speaker recognition
Translator Translate more than 100 languages and dialects
Video Indexer Extract actionable insights from your videos
Vision Analyze content in images and videos

 

 Computer vision Service in Azure

Computer Vision is an area of AI that deals with visual processing. Let’s explore some of the possibilities that computer vision brings.

The Seeing AI app is a great example of the power of computer vision. Designed for the blind and low vision community, the Seeing AI app harnesses the power of AI to open up the visual world and describe nearby people, text and objects.

Applications of Computer Vision

azure-ai-services-1.png

Computer Vision Services in Azure

azure-ai-services-2.png

Image Analysis with computer vision Service

/azure-ai-services-3.png

 

Training Models with custom vision Services

azure-ai-services-4.png

 

Detecting Face with Face Service

azure-ai-services-5.png

 

Reading Text with computer vision Service

 

Analys Forms with Form Recognizer Service

zure-ai-services-7.png

 

Analyze images with Computer Vision in Azure Portal

In this part we are going to analyze image in Azure portal as following:

  1. Start Azure Portal with your subscription, if you haven’t start free subscription here:
  2. In Search filed  search for “azure ai services then shall show you all Azure AI Services as followings:azure-ai-services-8.png
  3. Select Computer Vision from the left side under Azure AI Services
  4. Press to + Create button to create a Computer Vision Service
  5. Give a Resource Group name, Region, Name, Training Pricing Tier, Prediction pricing tier as follow:azure-ai-services-9.png
  6. Press to Review + create button,
  7. Press to new Create button, then Service is created
  8. Press to the  “Go to the Resource” then you see the following: azure-ai-services-10.png
  9. As you in the figure above, computer vision with name: mycv12345 is created and there key1, Key2, location, and Endpoint for this Service. These keys are used to access your Azure AI service API.

Run Service via Azure Cloud shell

  1. In the Azure Portal select Azure Cloud shell in the upper right as shown with:
  2. You need to create Storage, press to the Create Storage button then storage is created for your subscription and shows the Cloud shall as follow:
  3. In the Cloud shell, enter the following command to download the sample application and save it to a folder called ai-900.
  4. git clone https://github.com/MicrosoftLearning/AI-900-AIFundamentals ai-900
  5. Change Bash to Power Shell in the upper left of clould shell.
  6. The files are downloaded to a folder named ai-900. Now we want to see all of the files in your Cloud Shell storage and work with them. Type the following command into the shell, to show the fliles for edit.
  7. code .
  8. In the Files pane on the left, expand ai-900 and select Analyze-image.ps1. This file contains some code that uses the Computer Vision service to analyze image, as shown here:azure-ai-services-13.png
  9. The important thing is the endpoint URL and either of the keys for your Azure AI services resource. Copy these from the Keys and Endpoints page for your resource from the Azure portal and paste them into the code editor, replacing the YOUR_KEY and YOUR_ENDPOINT placeholder values respectively.

10. At the top right of the editor pane, use the … button to open the menu and select Save to save your changes. Then open the menu again and select Close Editor. Now that you’ve set up the key and endpoint, you can use your Azure AI services resource to extract Information from an image.

11. Let’s use the Read API. In this case, you have an advertising image for the fictional Northwind Traders retail company that includes some text.The sample client application will analyze the following image:

store-camera-1.jpg

 

12. In the PowerShell pane, enter the following commands to run the code to read the image:

cd ai-900 
./analyze-image.ps1 store-camera-1.jpg

13. Review the results of the image analysis, which include:

    • A suggested caption that describes the image.
    • A list of objects identified in the image.
    • A list of “tags” that are relevant to the image. shown as bellow:
PS /home/mehrdad/ai-900>  ./analyze-image.ps1 store-camera-1.jpg
Analyzing image...

Description:
a woman showing her phone to a child

Objects in this image:
 - cell phone
 - person
 - person
 - room

Tags relevant to this image:
 - text
 - person
 - woman
 - store
 - shop


PS /home/mehrdad/ai-900>

14. Now let’s try another image:

15. To analyze the second image, enter the following command:

./analyze-image.ps1 store-camera-2.jpg

16. Review the results of the image analysis for the second image: as following:


PS /home/mehrdad/ai-900> ./analyze-image.ps1 store-camera-2.jpg
Analyzing image...

Description:
a woman holding a shopping cart in a grocery store

Objects in this image:
 - person

Tags relevant to this image:
 - text
 - person
 - woman
 - marketplace
 - shop


PS /home/mehrdad/ai-900>

Note: To run a script in the current directory, type the path to the current directory, or use a dot to represent the current directory, followed by a path backslash ( . \ ).

This was for Computer Vision service in Azure AI Services.

You can test all other Services in Azure AI Service as exactly the same way (e.g. face recognition Service) look to the :  https://microsoftlearning.github.io/AI-900-AIFundamentals

Conclusion

In this post we have learned Azure AI Services and showed how to create Azure Computer Vision Service in Azure Portal and run it  Cloud Shell to analyze Images.

In my next post I will go AI Natural Language Processing

This post is part of  AI (Artificial Intelligence) step by step

 

Back to home page