Doctor of Philosophy in Computer Vision
Upon completion of the program requirements, the graduate will be able to:
Master the fundamental knowledge of computer vision and develop expertise in several specialized areas of research in computer vision.
Grow expertise in comprehending existing literature, apply reasoning, and master the necessary skills and techniques to develop novel ideas that are recognized by the experts of the computer vision discipline.
Apply advanced problem-solving skills to analyze, design and execute innovative solutions for the existing and/or new problems faced in both industry and academia.
Highly skilled in initiating, managing and completing technically challenging computer vision projects and be able to clearly communicate concepts, highly complex ideas and key findings in the form of technical reports, scientific publications and oral presentations at relevant technical venues.
Become an expert in selecting and using programming tools, libraries, and other relevant resources to solve real-world computer vision problems.
Develop an advanced ability to work independently with substantial authority or in team collaboration with professional integrity to complete highly challenging computer vision projects in a timely manner.
Develop a deep understanding of the existing body of knowledge and the ability to develop new knowledge in computer vision that makes students suitable for a role in academia or industry.
Practice research ethics and commit to professional responsibilities while conducting cutting edge advancements in computer vision discipline.
Understand legal, ethical, environmental and socio-cultural ramifications of computer vision technologies, and be able to take a lead in making informed and fair decisions on complex issues.
The minimum degree requirements for the Ph.D. in Computer Vision are 59 Credits, distributed as follows:
Core Courses: 4 Courses (15 Credit Hours)
Elective Courses: 2 Courses (8 Credit Hours)
Research Thesis: 1 Course (36 Credit Hours)
Ph.D. 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 eight in the list provided below:
Research Communication and Dissemination
Human and Computer Vision
Geometry for Computer Vision
Visual Object Recognition and Detection
Advanced Computer Vision
Advanced 3D Computer Vision
Neural Networks for Object Recognition and Detection
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 Ph.D. in Computer Vision are listed in below table:
Mathematical Foundations for Artificial Intelligence
Data Structures and Algorithms
Big Data Processing
Advanced Machine Learning
Probabilistic and Statistical Inference
Natural Language Processing
Advanced Natural Language Processing
Medical Imaging: Physics and Analysis
The Ph.D. thesis exposes students to cutting-edge and unsolved research problems in the field of Computer Vision, where they are required to propose new solutions and significantly contribute to the body of knowledge. Students pursue an independent research study, under the guidance of a supervisory panel, for a period of 3-4 years.
Ph.D. Research Thesis