Course contents *

Overview of goals and methods of image analysis and computer vision.

Introduction to biological vision and visual perception.

Basic image analysis: signal theory, filtering, image enhancement, image reconstruction, segmentation, classification, representation.

Basic computer vision: multi-scale representation, detection of contours and other features.

Perspective projection.

Illumination models. Texture. Stereo. Motion.

Object recognition.

Intended learning outcomes *

After completing the course you will be able to:

• identify basic concepts, terminology, theories, models and methods in the field of computer vision, image analysis and image processing,
• describe known principles of human visual system,
• develop and systematically test different basic methods of computer vision, image analysis and image processing,
• experimentally evaluate different image analysis algorithms and summarize the results,
• choose appropriate image processing methods for image filtering, image restauration, image reconstruction, segmentation, classification and representation,
• describe basic methods of computer vision related to multi-scale representation, edge detection and detection of other primitives, stereo, motion and object recognition,
• build a toolbox for image processing consisting of methods for grey-level transformations, image filtering functions and methods for edge and corner detection,
• suggest a design of a computer vision system for a specific problem

in order to

• get acquainted with basic possibilities and constraints of computer vision, image processing and image analysis and therefore assess which problems can be solved in the field of robotics, medical and industrial image processing, processing of satelite images and similar,
• be able to implement, analyse and evaluate simple systems for automatic image processing and computer vision,
• have a broad knowledge base so to easily read the related literature.

Course Disposition

Lectures: 28 h
Tutorials: 4 h
Laboratory assignments: 20 h

Specific prerequisites *

No information inserted

Recommended prerequisites

The courses in the basic block on mathematics, computer science and numerical analysis on the D-, E- or F-programme. One more course on signal processing and/or numerical analysis can be recommended. We recommend the students to read the course during the fourth year because it uses prerequisites from a relative wide spectrum of applied mathematics and computer science.

Equipment

No information inserted

Literature

R. C. Gonzalez and R. E. Woods: Digital Image Processing Prentice Hall, 2003.

Grading scale *

A, B, C, D, E, FX, F

Examination *

• LAB1 - Laboratory Work, 3.0 credits, Grading scale: P, F
• TEN1 - Examination, 3.0 credits, Grading scale: A, B, C, D, E, FX, F

Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.

The examiner may apply another examination format when re-examining individual students.

Other requirements for final grade *

Examination (TEN1; 3 university credits).
Laboratory assignments (LAB1; 3 university credits).

Opportunity to complete the requirements via supplementary examination

No information inserted

Opportunity to raise an approved grade via renewed examination

No information inserted

Examiner

Hans Åke Stefan Carlsson

Course web

No information inserted

Offered by

CSC/Computer Science

Main field of study *

No information inserted

Education cycle *

Second cycle

Add-on studies

DD2427 Image Based Recognition and Classification and DD2428 Geometry and Visualization.

Contact

Danica Kragic, tel: 790 6729, e-post: danik@nada.kth.se

Ethical approach *

• All members of a group are responsible for the group's work.
• In any assessment, every student shall honestly disclose any help received and sources used.
• In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.