Program details
Introduction
This scientific field studies how computers can be used to automatically understand and interpret visual imagery. It aims to mimic the astounding capabilities of human visual cortex using machine vision algorithms. It studies how an image is created, the geometry of the 3D world and high-level tasks such as object recognition, object detection, and tracking, image segmentation and action recognition. Computer vision has important applications in augmented/virtual reality, autonomous cars, service robots, biometrics and forensics, remote sensing and security and surveillance.
Program
Competence
Upon completion of the program requirements, the graduate will be able to:
- Exhibit comprehensive and highly specialized knowledge of computer vision in line with the underlying mathematical and computational principles.
- Perform critical literature survey and develop new ideas by integrating multidisciplinary knowledge.
- Apply advanced problem-solving skills to analyze, design and execute solutions for the existing and new problems in computer vision faced by both industry and academia.
- Become highly skilled in initiating, managing, and completing multifaceted computer vision projects, and be able to clearly communicate concepts, complex ideas and conclusions both orally and in the form of technical reports.
- Function independently and in a team to address computer vision problems under complex and unpredictable real-world settings.
- Demonstrate a fundamental understanding of computer vision discipline at an advanced level suitable to pursue a PhD degree and contribute to cutting-edge computer vision research to produce new knowledge or take responsibility to lead innovative and impactful computer vision projects in industry.
- Manifest the right learning attitude during coursework and research that clearly shows ownership, personal and technical growth and responsibility.
- Understand legal, ethical, environmental and socio-cultural ramifications of computer vision technologies, and be able to make informed and fair decisions on complex practical issues.
The minimum degree requirements for the “master’s in computer Vision” are 35 Credits, distributed as follows:
Core Courses
Master’s in Computer Vision is primarily a research-based degree. The purpose of coursework is to equip students with the right skillset, so they can successfully accomplish their research project (thesis). Students are required to take COM701 as a mandatory course. They can select three core courses from a concentration pool of six in the list provided below:
Research Communication & Dissemination*
Human and Computer Vision
Geometry for Computer Vision
Visual Object Recognition and Detection
Mathematical Foundations for Artificial Intelligence
Artificial Intelligence
Deep Learning
Elective Courses
Students will select a minimum of two elective courses, with a total of eight (or more) credit hours (CH) from a list of available elective courses based on interest, proposed research thesis, and career perspectives, in consultation with their supervisory panel. The elective courses available for the Master’s of Machine Learning are listed in the below table:
Optimization
Advanced Programming
Data Structures and Algorithms
Data Mining
Big Data Processing
Machine Learning
Advanced Machine Learning
Probabilistic and Statistical Inference
Natural Language Processing
Advanced Natural Language Processing
Speech Processing
Advanced Computer Vision
Advanced 3D Computer Vision
Neural Networks for Object Recognition and Detection
Medical Imaging: Physics and Analysis
Research Thesis
Master’s thesis research exposes students to an unsolved research problem, where they are required to propose new solutions and contribute towards the body of knowledge. Students pursue an independent research study, under the guidance of a supervisory panel, for a period of 1 year.
Master's Research Thesis