Teacher in charge: Petri Rönnholm: petri.ronnholm@aalto.fi

Lectures

Onsite lectures are given in hall k202 (Otakaari 4), but the sessions are recorded enabling a hybrid learning. The recordings are published after the lectures.

Week 2, Tue 9.1., 12:15-14:00, Lecture 1, digital image processing 1, hall k202

Week 2, Thu 11.1., 10:15-12:00, Lecture 2, digital image processing 2, hall k202

Week 3, Tue 16.1., 12:15-14:00, Lecture 3, digital image processing 3, hall k202

Week 3, Thu 18.1., 10:15-12:00, Lecture 4, digital image processing 4, hall k202

Week 4, Tue 23.1., 12:15-14:00, Lecture 5, digital image processing 5, hall k202

Week 4, Thu 25.1., 10:15-12:00, Lecture 6, feature extraction 1, hall k202

Week 5, Tue 30.1., 12:15-14:00, Lecture 7, feature extraction 2, hall k202

Week 5, Thu 1.2., 10:15-12:00, Lecture 8, feature extraction 3, hall k202

Week 6, Tue 6.2., 12-14, Lecture 9, feature extraction 4, hall k202

Week 6, Thu 8.2., 10-12. Lecture 10, Neural Networks, hall k202

Week 7, Tue 13.2., 12:15-16:00, Seminar, hall U135a U7 PWC (Otakaari 1), hopefully as many as possible can physically attend. If you can attend only remotely, take contact with petri.ronnholm@aalto.fi in advance

Week 7, Thu 16.2., 10-12. NO LECTURE

Week 8, Tue 20.2., 12-15 Lecture exam, hall 215

 

Compulsory assignments

(all compulsory assignments must be passed to get the final grade of the course)

Assignment 1. From an image sensor to an image file, deadline 19.1. (help: Petri Rönnholm petri.ronnholm@aalto.fi, evaluation: Toni Rantanen, toni.rantanen@aalto.fi)

Assignment 2. Sampling of a signal, and interpretation of Fourier spectrums of images, deadline 26.1. (Petri Rönnholm, petri.ronnholm@aalto.fi) 

Assignment 3. Digital image processing with Matlab, Deadline 2.2., includes Matlab scripting (Milka Nuikka, milka.nuikka@aalto.fi)

Assignment 4. Seminar, 13.2., 12:15-16:00, hall k202

Assignment 5. Plessley-Harris interest operator, Deadline 22.2., includes Matlab programming (Petri Rönnholm, petri.ronnholm@aalto.fi)

 

Voluntary assignment

From this assignment, you can get 3 extra points

Assignment 6. Teaching YOLO convolutional neural network to detect teekkari caps with Matlab, pre-written code i.e. includes no programming, deadline 25.2.


To pass the course, you need to have all compulsory assignments accepted and examination passed. The final grade is a combination of assignments and examination grade. The maximum points from compulsory assignments is á 30 points, i.e., total of 150 points (plus voluntary assignment 3 points). This is scaled (no rounding) to range [0, 5]. If the assignment report is returned after the deadline, the maximum point from that assignment is 12 points (equals to grade 2).

The lowest grade to pass the examination is 15/30 points.

The final grade is the rounded average of the assignment and examination grades

E.g.

exam = 2, assignments = 4.5, grade = 3.25 -> 3

exam = 5, assignments = 3, grade = 4


Last modified: Tuesday, 9 January 2024, 3:39 PM