AUT-2802 Machine Vision - 10 stp

Introduction to machine vision: fundamentals of image formation and camera parameters. An overview of Image sensing pipeline, Demosaicing, and Compression.

Fundamentals of supervised learning, unsupervised learning, reinforcement learning, and ethics in Deep learning.

Training deep learning models, loss functions, gradients, initialization, evaluation of performance in Deep learning.

Fundamentals of technical and scientific report writing with emphasis on performing experiments and data analysis.

Fundamentals of programming using Python for Deep learning applications.

Knowledge:

This interdisciplinary course should give the candidate a good understanding of fundamentals of machine vision with special focus on application of deep learning in a case study or application.

Skills:

• Candidate will build knowledge in image formation, cameras, and vision sensors.
• Candidate will learn about deep learning and subtopics such as: supervised learning, unsupervised learning, reinforcement learning, and ethics in deep learning.
• Candidate will learn about training deep learning models, loss functions, gradients, initialization, and performance evaluation in deep learning.
• Candidate should be able to understand and use the knowledge from machine vision in their selected application or task.
• Candidate should be able to demonstrate their knowledge using Python.
• Candidate should be able to demonstrate scientific analysis of data or experiments in a case study report.