Computer Vision

Programme Overview

In this module, you will gain an introduction to computer vision when building artificially intelligent systems that process and perceive visual data through deep learning algorithms such as neural networks. Topics will include fundamentals of image formation and camera imaging processing including types of features such as stereo image, filtering, feature extraction, edge detection, alignment, object recognition, appearance, audio, language, and other functionality. You will research situations where imagery enhances artificial intelligence to capture the eye of the intended audience such as for gaming systems, self-driving cars, medical imaging, scientific applications, and other advancements in technology. As a result, you will understand how visual representations can be structured to make images more accurate depictions through computer vision tasks. 

Learning Outcomes

1. Describe the purpose of computer vision and the various application scenarios it can be used in.
2. Explain how deep learning algorithms work to support computer vision such as neural networks.
3. Evaluate computer vision techniques such as image filtering, edge detection, and video analysis to understand how each function solves a problem. 
4. Execute computer vision tests for various solutions to report on the results.
5. Create a solution to a problem in computer vision to report on the outcome.