This module focuses on the rapidly advancing and closely related fields of image processing and computer vision, which utilize artificial intelligence techniques to derive meaningful information from image, video, and other visual data. Divided into two parts, the first part of the module will cover fundamental techniques in image processing including acquiring, processing, enhancing image signal; the second part will cover techniques and applications in image/video analysis and computer vision, i.e., analysing and extracting high level information from the world from images in a similar way to humans. The module will be delivered in a practical manner and students will be asked to code algorithms in Python to demonstrate deep and practical understanding of cutting-edge research in image processing and computer vision to solve real-life vision problems.
A Demonstrate a comprehensive and systematic understanding of the mathematical foundations and algorithmic principles of digital image processing (IP) and computer vision (CV). B Implement different IP and CV algorithms and models, and evaluate them based on appropriate performance metrics. C Demonstrate expert knowledge to offer critical insight into the current state-of-the-art image processing and computer vision technologies. D Expertly analyse real-world IP/CV problems and critically appraise the development of appropriate algorithms used for implementing IP and CV.
The teaching philosophy of the module follows very much the philosophy of Syntegrative Education. This has meant that the teaching delivery pattern, which follows more intensive block teaching, allows more meaningful contribution from industry partners. This philosophy is carried through also in terms of assessment, with reduction on the use of exams and increase in coursework, especially problem-based assessments that are project focused. The delivery pattern provides space in the semester for students to concentrate on completing the assessments. Students are expected to attend two two-hour formal lectures, a one-hour tutorial and a three-hour lab session in a typical block teaching week. The lectures cover the content outlined in the syllabus, providing a comprehensive understanding of image processing and computer vision topics. Tutorials aim to deepen students' comprehension by fostering critical thinking through group discussions and case studies focused on specific topics or research papers. These discussions facilitate exploration of state-of-the-art techniques in image processing and computer vision. Labs are designed to equip students with essential programming skills in module-related areas. Through hands-on exercises and projects, students gain practical experience in implementing and experimenting with image processing and computer vision algorithms. In addition, students will be expected to devote unsupervised time to private study. Private study will provide time for reflection and consideration of lecture material and background reading.