Computer Engineering MA, Advanced Image Processing, 6 credits

Aim

The course aims to give a good understanding of theoretical concepts and practical skills in advanced image processing, using model-based and machine learning-based methods.

Course objectives

Upon completion of the course the student should be able to:

• Explain key concepts of advanced image processing, including inverse problems in imaging, regularization techniques, and compressed sensing.
• Analyze different methods for image restoration, including denoising, deblurring, inpainting, and super-resolution.
• Compare traditional approaches with learning-based methods for various advanced image processing tasks.
• Design and develop algorithms for advanced imaging applications.
• Select and evaluate appropriate techniques for specific image processing challenges based on theoretical and practical considerations.

Content

The course includes:

• Fundamental concepts of inverse problems in imaging, including problem formulation, regularization techniques, and optimization-based solutions
• Image restoration methods, including denoising, deblurring, inpainting, and super-resolution using traditional and learning-based approaches
• Compressed sensing and sparse representations, including basis selection, dictionary learning, and optimization techniques for image reconstruction
• Unrolling and model-based learning, including interpretable architectures that bridge optimization methods with deep learning

Entry requirements

Computer Engineering or Electrical Engineering, 60 credits, including programming, 10 credits, Signal and Image Processing, 6 credits, Computer Vision, 6 credits, Optimization, 6 credits, and Data Mining and Machine Learning, 6 credits.

Mathematical subjects, 30 credits, including Probability Theory and Statistics, and Linear Algebra.

Selection rules and procedures

The selection process is in accordance with the Higher Education Ordinance and the local order of admission.

Teaching form

The course is taught using lectures, exercises and laboratory sessions. A sizeable part of the course is with limited supervision, where the student is assumed to work on lecture material, exercises, and laboratory work.

Teaching can take place in Swedish or English.

Examination form

L101: Laboratory work, 1.5 Credits
Grade scale: Two-grade scale

T101: Written exam, 4.5 Credits
Grade scale: Seven-grade scale, A-F o Fx

Link to grading criteria: https://www.miun.se/gradingcriteria

The examiner has the right to offer alternative examination arrangements to students who have been granted the right to special support by Mid Sweden University’s disabilities adviser.

Examination restrictions

Students registered on this version of the syllabus have the right to be examined 3 times within 1 year according to specified examination forms. After that, the examination form applies according to the most recent version of the syllabus.

Grading system

Seven-grade scale, A-F o Fx