Computer vision fundamentals

Module title:

Computer vision fundamentals

Module overview:

This module introduces students to computer vision applications based on deep learning. Deep learning is a trend in research and development in machine learning. Deep learning methods have carried ground-breaking advances in computer vision. They can solve many complex problems of computer vision which were not easily solved by machine learning.

Students who take this module will gain knowledge and skills in deep learning and its application to computer vision, contributing significantly to students development as professionals in the fields between software engineering and data science.

The module is taught in Python programming language. The module assessment is based on solving a series of smaller practical tasks and on individual student projects. In these projects, students must create a solution based on computer vision.

Students will learn:

About image classification algorithms, detection and localization techniques.

About segmentation methods and transfer learning concepts.

How to program a software solution based on deep machine-learning concepts.

Literature:

Required readings:
1. Elgendy, M. (2020) Deep Learning for Vision Systems. Shelter Island: Manning Publications.

Supplementary readings:
1. Géron, A. (2019) Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. Sebastopol: O´Reilly Media.
2. Ranjan, S. and Senthamilarasu, S. (2020) Applied Deep Learning and Computer Vision for Self-Driving Cars: Build autonomous vehicles using deep neural networks and behavior-cloning techniques. Birmingham: Packt Publishing.