Nazlı İkizler Cinbiş

Teaching

AID 401 Fundamentals of Computer Vision

How computers make sense of images and video: from image formation and filtering to modern deep learning models for recognition.

Course information

This course introduces the fundamental problems and methods of computer vision. We start with how images are formed and represented, and cover filtering, edge and feature detection, feature matching, image alignment and motion estimation. The second half of the course focuses on visual recognition with machine learning and deep learning: convolutional networks, object detection, segmentation, recurrent models, video and human action understanding, and recent vision transformer and vision-language models. Students will implement core algorithms in Python.

Instructor and time

Reference books

Grading

ComponentWeight
Project20%
Midterm35%
Final exam45%

Announcements

All announcements and communication will be carried out via Piazza. The enrolment link and lecture notes will be shared there at the start of the semester.

Schedule

Tentative. Dates and lecture notes will be added during the semester.

WeekTopicNotes
1Introduction and image formation
2Image filtering and the frequency domain
3Edge detection
4Feature detection and description
5Feature matching, image alignment and RANSAC
6Motion estimation
7Midterm
8Machine learning for visual recognition
9Convolutional neural networks
10Object detection and segmentation
11Recurrent models
12Video and human action understanding
13Vision transformers and vision-language models
14Project presentations

Useful links