Who is this course for?
This course presents computer vision and deep learning techniques. It is designed for students with a background in computer science who want to gain additional skills in how machine learning is applied in computer vision.
What will you learn from this course?
You will learn about computer vision concepts, both from a theoretical and practical perspective. The primary content includes: Image acquisition, representation, and transformation. Low-level vision (edges, corners, lines, and circles detection). Feature extraction using deep neural networks and transfer learning. Image pattern classification. Computer vision applications, including: Facial image analysis, In-vehicle vision system (driver drowsiness), Robot vision systems (human emotion and intention detection).
What is the format for this course?
Instruction type: The course is delivered fully online and in English.
Frequency: Weekly lectures and assignments over approximately two months.
Examination: Grade based on three practical assignments, demanding submission of report and associated programming code before a specific deadline.
Course responsible:
Fernando Alonso-Fernandez
Email: fernando.alonso-fernandez [AT] hh [DOT] se