Skip to main content

Computer Vision: What does Ai see in the real world on Microsoft platform?

Author by Lwin Maung

Computer Vision: What does Ai see in the real world on Microsoft platform?

Microsoft Cognitive Services allows for your applications, websites, or services to become more aware of the natural surroundings by giving ability to hear, see, speak, and understand the user and environment around the user. Currently, there are 6 out of box services that are offered thru the cognitive services suite of products:

  • Vision
  • Speech
  • Knowledge
  • Search
  • Language
  • and Anomaly Detection.




In this blog post (and a few more to follow), we will be talking about the vision service and api and capabilities that are provided as an out of box experience. Within the Vision services, Microsoft offers sub catagories. Computer vision, Face, Video Indexer, Content Moderator,  and Custom vision. In the past, we have talked about Face API and services related to Face (here).




So, what can a computer see? Do android dream of electric sheep? Computer vision service allowes for sub services that are specifically skilled to solve a particular problem or a challange.


Scene and Activity recognition:

This feature returns information about visual content found in an image. Use tagging, domain-specific models, and descriptions in four languages to identify content and label it with confidence. Use Object Detection to get location of thousands of objects within an image.



Celebrity and Landmark Detection:

Recognize more than 1,000,000 celebrities from business, politics, sports and entertainment, as well as 9,000 natural and manmade landmarks from around the world.


Optical Character Recognition:

Detect text in an image using optical character recognition (OCR) and extract the recognized words into a machine-readable character stream. Analyze images to detect embedded text, generate character streams, and enable searching.


Handwriting Recognition:

Detect and extract handwritten text from notes, letters, essays, whiteboards, forms, and other sources. Handwritten OCR works with different surfaces and backgrounds, such as white paper, yellow sticky notes, and whiteboards.


In the next few posts, we will discover how we can integrate features such as computer vision into your project.