Applied Artificial Intelligence: Computer Vision and Image Analysis

Gain machine learning and AI skills

This course is part of the Advanced and Applied AI on Microsoft Azure ExpertTrack, helping you develop AI and machine learning skills and prepare you for the relevant Microsoft microcredentials.

When we look at an image, we are able to pick out meaning based on what we see. When computers are presented with an image, it will usually see nothing unless we use computer vision, a way to extract information and understand the visual world.

During this course, you’ll learn all about Image Analysis techniques and why computer vision is important in AI. You’ll explore classical Image Analysis techniques such as Edge Detection, Watershed and Distance Transformation, as well as K-means clustering to increase your knowledge on this AI component.

Explore the evolution of image analysis

You’ll learn the evolution of Image Analysis to understand the background of this field of AI.

By the end of the course, you’ll be able to compare classical and deep learning object classification techniques and apply them to modern AI technologies.

Segment images using OpenCV and Microsoft Cognitive Toolkit

You’ll gain hands-on experience using OpenCV and the Microsoft Cognitive Toolkit to segment images into meaningful parts and further strengthen your knowledge of computer vision.

In OpenCV, you’ll learn how to implement classic Image Analysis algorithms and you’ll also understand how to train a model to perform Semantic Segmentation using Transfer Learning and Microsoft ResNet. These are transferable skills you will use time and time again when dealing with computer vision in AI.

This course is for anyone interested in computer vision, with an understanding of the basics of image processing.

This course is for anyone interested in computer vision, with an understanding of the basics of image processing.

• Apply classical Image Analysis techniques, such as Edge Detection, Watershed and Distance Transformation as well as K-means Clustering to segment a basic dataset.
• Implement classical Image Analysis algorithms using the OpenCV library.
• Compare classical and Deep-Learning object classification techniques.
• Apply Microsoft ResNet, a deep Convolutional Neural Network (CNN) to object classification using the Microsoft Cognitive Toolkit.