Learning Microsoft Cognitive Services - Third Edition

Book description

Build smarter applications with AI capabilities using Microsoft Cognitive Services APIs without much hassle

Key Features

  • Explore the Cognitive Services APIs for building machine learning applications
  • Build applications with computer vision, speech recognition, and language processing capabilities
  • Learn to implement human-like cognitive intelligence for your applications

Book Description

Microsoft Cognitive Services is a set of APIs for adding intelligence to your application and leverage the power of AI to solve any business problem using the cognitive capabilities.

This book will be your practical guide to working with cognitive APIs developed by Microsoft and provided with the Azure platform to developers and businesses. You will learn to integrate the APIs with your applications in Visual Studio. The book introduces you to about 24 APIs including Emotion, Language, Vision, Speech, Knowledge, and Search among others. With the easy-to-follow examples you will be able to develop applications for image processing, speech recognition, text procession, and so on to enhance the capability of your applications to perform more human-like tasks. Going ahead, the book will help you work with the datasets that enable your applications to process various data in form of image, videos, and texts.

By the end of the book, you will get confident to explore the Cognitive Services APIs for your applications and make them intelligent for deploying in businesses.

What you will learn

  • Identify a person through visual and audio inspection
  • Reduce user effort by utilizing AI-like capabilities
  • Understand how to analyze images and texts in different ways
  • Analyze images using Vision APIs
  • Add video analysis to applications using Vision APIs
  • Utilize Search to find anything you want
  • Analyze text to extract information and explore text structure

Who this book is for

Learning Microsoft Cognitive Services is for developers and machine learning enthusiasts who want to get started with building intelligent applications without much programming knowledge. Some prior knowledge of .NET and Visual Studio will help you undertake the tasks explained in this book.

Table of contents

  1. Learning Microsoft Cognitive Services - Third Edition
    1. Table of Contents
    2. Learning Microsoft Cognitive Services - Third Edition
      1. Why subscribe?
      2. PacktPub.com
    3. Contributors
      1. About the author
    4. Acknowledgments
      1. About the reviewer
      2. Packt is Searching for Authors Like You
    5. Preface
      1. Who this book is for
      2. What this book covers
      3. To get the most out of this book
        1. Download the example code files
        2. Download the color images
        3. Conventions used
      4. Get in touch
        1. Reviews
    6. 1. Getting Started with Microsoft Cognitive Services
      1. Cognitive Services in action for fun and life-changing purposes
      2. Setting up the boilerplate code
      3. Detecting faces with the Face API
      4. An overview of different APIs
        1. Vision
          1. Computer vision
          2. Face
          3. Video indexer
          4. Content moderator
          5. Custom vision service
        2. Speech
          1. Bing Speech
          2. Speaker recognition
          3. Translator speech API
        3. Language
          1. Bing Spell Check
          2. Language Understanding Intelligent Service (LUIS)
          3. Text analytics
          4. Translator Text API
        4. Knowledge
          1. Project Academic Knowledge
          2. Knowledge exploration
          3. Recommendations solution
          4. QnA Maker
          5. Project Custom Decision Service
        5. Search
          1. Bing Web Search
          2. Bing Image Search
          3. Bing Video Search
          4. Bing News Search
          5. Bing Autosuggest
          6. Bing Visual Search
          7. Bing Custom Search
          8. Bing Entity Search
      5. Getting feedback on detected faces
      6. Summary
    7. 2. Analyzing Images to Recognize a Face
      1. Analyze an image using the Computer Vision API
        1. Setting up a chapter example project
        2. Generic image analysis
        3. Recognizing celebrities using domain models
        4. Utilizing optical character recognition
        5. Generating image thumbnails
      2. Diving deep into the Face API
        1. Retrieving more information from the detected faces
        2. Deciding whether two faces belong to the same person
        3. Finding similar faces
        4. Grouping similar faces
      3. Adding identification to our smart-house application
        1. Creating our smart-house application
        2. Adding people to be identified
          1. Creating a view
          2. Adding person groups
          3. Adding new persons
          4. Associating faces with a person
          5. Training the model
          6. Additional functionality
        3. Identifying a person
      4. Knowing your mood using the Face API
        1. Getting images from a web camera
        2. Letting the smart house know your mood
      5. Automatically moderating user content
        1. Types of content moderation APIs
          1. Image moderation
          2. Text moderation
        2. Moderation tools
          1. Using the
          2. Other tools
      6. Building your own image classifiers
        1. Building a classifier
        2. Improving the model
        3. Using the trained model
      7. Summary
    8. 3. Analyzing Videos
      1. Diving into Video Indexer
        1. General overview
          1. Typical scenarios
          2. Key concepts
            1. Breakdowns
            2. Summarized insights
            3. Keywords
            4. Sentiments
            5. Blocks
      2. Unlocking video insights using Video Indexer
        1. How to use Video Indexer
          1. Through a web portal
          2. Video Indexer API
      3. Summary
    9. 4. Letting Applications Understand Commands
      1. Creating language-understanding models
        1. Creating an application
        2. Recognizing key data using entities
        3. Understanding what the user wants using intents
        4. Simplifying development using prebuilt models
        5. Prebuilt domains
      2. Training a model
        1. Training and publishing the model
        2. Connecting to the smart house application
        3. Model improvement through active usage
          1. Visualizing performance
          2. Resolving performance problems
            1. Adding model features
            2. Adding labeled utterances
            3. Looking for incorrect utterance labels
            4. Changing the schema
          3. Active learning
      3. Summary
    10. 5. Speaking with Your Application
      1. Converting text to audio and vice versa
        1. Speaking to the application
        2. Letting the application speak back
          1. Audio output format
          2. Error codes
          3. Supported languages
        3. Utilizing LUIS based on spoken commands
      2. Knowing who is speaking
        1. Adding speaker profiles
        2. Enrolling a profile
        3. Identifying the speaker
      3. Verifying a person through speech
      4. Customizing speech recognition
        1. Creating a custom acoustic model
        2. Creating a custom language model
        3. Deploying the application
      5. Translating speech on the fly
      6. Summary
    11. 6. Understanding Text
      1. Setting up a common core
        1. New project
        2. Web requests
        3. Data contracts
      2. Correcting spelling errors
      3. Extracting information through textual analysis
        1. Detecting language
        2. Extracting key phrases from text
        3. Learning whether a text is positive or negative
      4. Translating text on the fly
        1. Translating text
        2. Converting text script
        3. Working with languages
          1. Detecting the language
          2. Getting supported languages
      5. Summary
    12. 7. Building Recommendation Systems for Businesses
      1. Providing personalized recommendations
        1. Deploying the Recommendation Solution template in Azure
        2. Importing catalog data
        3. Importing usage data
        4. Training a model
          1. Starting to train
          2. Verifying the completion of training
        5. Consuming recommendations
          1. Recommending items based on prior activities
      2. Summary
    13. 8. Querying Structured Data in a Natural Way
      1. Tapping into academic content using the academic API
        1. Setting up an example project
      2. Interpreting natural language queries
      3. Finding academic entities in query expressions
      4. Calculating the distribution of attributes from academic entities
      5. Entity attributes
      6. Creating the backend using the Knowledge Exploration Service
      7. Defining attributes
      8. Adding data
      9. Building the index
      10. Understanding natural language
      11. Local hosting and testing
      12. Going for scale
        1. Hooking into Microsoft Azure
        2. Deploying the service
      13. Answering FAQs using QnA Maker
      14. Creating a knowledge base from frequently asked questions
      15. Training the model
      16. Publishing the model
      17. Summary
    14. 9. Adding Specialized Searches
      1. Searching the web using the smart-house application
        1. Preparing the application for web searches
        2. Searching the web
      2. Getting the news
        1. News from queries
        2. News from categories
        3. Trending news
      3. Searching for images and videos
        1. Using a common user interface
        2. Searching for images
        3. Searching for videos
      4. Helping the user with autosuggestions
        1. Adding autosuggest to the user interface
        2. Suggesting queries
      5. Search commonalities
        1. Languages
        2. Pagination
        3. Filters
          1. Safe search
          2. Freshness
        4. Errors
      6. Searching for visual content using Bing Visual Search
        1. Sending a request
        2. Receiving a response
      7. Adding a custom search
        1. Typical workflow
          1. Consuming the search instance
      8. Summary
    15. 10. Connecting the Pieces
      1. Completing our smart-house application
        1. Creating an intent
        2. Updating the code
          1. Executing actions from intents
          2. Searching news on command
          3. Describing news images
      2. Real-life applications using Microsoft Cognitive Services
        1. Uber
        2. DutchCrafters
        3. CelebsLike.me
        4. Pivothead
        5. Zero Keyboard
        6. The common theme
      3. Where to go from here
      4. Summary
    16. A. LUIS Entities
      1. LUIS prebuilt entities
    17. B. License Information
      1. Video Frame Analyzer
      2. OpenCvSharp3
      3. Newtonsoft.Json
      4. NAudio
        1. Definitions
        2. Grant of Rights
          1. Conditions and Limitations
    18. Index

Product information

  • Title: Learning Microsoft Cognitive Services - Third Edition
  • Author(s): Leif Larsen
  • Release date: September 2018
  • Publisher(s): Packt Publishing
  • ISBN: 9781789800616