Type of course

Admission requirements

Admission requirements are generell studiekompetanse + SIVING.

Local admission, application code 9391 - singular courses in engineering sciences. The course is also available to exchange students and Fulbright students.

Course content

The course introduces fundamental topics in digital image analysis, comprising both mathematical operations on images (image processing) and their use in image understanding and interpretation (computer vision). The course covers mathematical characterization of discrete images, sampling, reconstruction and important image transforms. It teaches image filtering in the spatial and frequency domain covering image enhancements, noise removal, and detection of edge, point and corner features that can be used in vision tasks. It also covers algorithms for object detection and extraction, including thresholding, segmentation and classification. The course describes the evolution from image filtering by convolution with static operators to adaptive processing with convolutional neural networks (CNNs) that learn their filters from data. It gives an introduction to deep learning and training of CNNs for image analysis tasks. The course emphasizes practical exercises. It is relevant for further studies in various fields, such as machine learning, remote sensing (earth observation, space physics, optics, microwaves and ultrasound), automation, robotics, and energy data analytics.

Fundamental knowledge of programming is presupposed.

Recommended prerequisites

Objectives of the course

Knowledge - The student can:

• Describe fundamental image processing techniques
• explain the theory behind and application domain of various basic intensity transforms, spatial and frequency domain filters
• explain the main functionality of convolutional neural networks for certain image analysis tasks
• evaluate different image processing techniques for application to a given problem

Skills - The student can:

• use basic image processing techniques to solve a given problem
• perform image restoration and reconstruction
• perform image segmentation and thresholding
• train a convolutional neural network for given image analysis tasks

General competence - The student can:

• implement image analysis techniques in a programming language
• interpret and discuss various image analysis techniques

Language of instruction and examination

Teaching methods

Lectures: 40 hours

Exercises: 40 hours

Information to incoming exchange students

This course is open for inbound exchange students.

Do you have questions about this module? Please check the following website to contact the course coordinator for exchange students at the faculty: INBOUND STUDENT MOBILITY: COURSE COORDINATORS AT THE FACULTIES | UiT

Recommended reading/syllabus