Course Code

MAICOVI6

Credits

6 EC

Time Period

Semester 1, block 1 and 2

Objectives

Students will develop insights and gain practical experience in the theory, methods, and algorithms for advanced computer vision techniques.

The field of computer vision is by impact one of the most forefront fields of AI. Computer vision has matured to a degree that many applications have become possible or nearly are possible. In this course, computer vision is seen as an enterprise that uses statistical methods to disentangle image data using models constructed from geometry, physics, and machine learning. The course aspires a thorough understanding of many of the current techniques, aiming at a broad basis, and extending to state of the art methods. Topics range from basic edge detection, image representation, texture analysis, (photometric) stereo, and multiple view geometry, to sophisticated techniques of model based vision, material recognition, tracking, object detection, and scene classification. To appreciate the nowadays possibilities, practical experience will be gained with some state-of-the-art techniques.

Format

Reading, discussing, and presenting of the book chapters (Reading group format)
Lab exercises in Matlab
Evaluation and poster presentation of a state-of-the-art research paper

Study materials

Forsyth and Ponce, Computer Vision: a modern approach, Prentice Hall.

Assessment

Examination and practical assignments.

Profile Project AI - Intelligent Systems

Course Code

MAIPPIS6

Credits

6 EC

Time Period

Semester 2, block 3

Objectives

Project-based research.

The project includes an in-depth study on the different topics, which were educated during the various courses, and to put them into practice. First, the students will do a study on related literature. Then, computational methods are developed and implemented. Finally, a report is written and a presentation is given about the work. Each year a number of different topics will be discussed. The project is focused on the preparation of the students for their actual graduation work.

Format

Project based research in groups

Study materials

articles

Assessment

Report and presentation.

Linear Algebra and Matlab

Course code

MAILAML3

Credits

3 EC

Time Period

Semester 1, block 1

Objectives

To acquire basic knowledge of Linear Algebra and MatLab.

This course provides the basics of vector and matrix calculus, aimed at application in the machine learning and computer vision courses. During the practicum students will be trained in Matlab.

Format

Lectures
Homework assignments
Lab exercises in Matlab

Study materials

Otto Bretscher, Linear Algebra with Applications.

Assessment

Examination and practical assignments.

Remarks

This course is intended to cope with deficiencies in elementary algebra skills.

Amsterdam University College

Intelligent Systems

Course Code

SCI293

Credits

6 EC

Time Period

Semester 1

Lecture outcomes

Students are able to understand and evaluate signal processing methodologies for various sensory modalities and their relation to human perception. They acquire a basic knowledge of machine perception and are able to apply machine perception methods in relation to human perception.

This course provides an introduction to sensory information processing for machines. It covers visual, audio, language, and haptic perception for artificial systems. The course provides the fundamental signal processing background, mainstream machine learning methodologies, and the background and analogies for human perception. Topics include:

Perception basics for visual, audio, speech, and haptic perception
Representation of sensory information
Receptive field measurements
Linear and Fourier theory
Invariant transformations
Combining information streams
Error and uncertainty propagation
Machine learning principles for sensory information processing
Experimental evaluation and design

Study materials

John Coleman (University of Oxford), "Introducing Speech and Language Processing" Cambridge University Press (Cambridge introductions to language and linguistics), 2005, xi+301 pp.