This graduate course is about the fundamentals of computer vision, which is a field of artificial intelligence (AI) that applies machine learning to images and videos to understand media and make decisions about them. With computer vision, we can, in a sense, give vision to software and technology.
The aim of this course is to demonstrate students a broad understanding of computer vision, its applications and theoritical background. Moreover, our another goal is to enable them implement their simple applications in this highly popular field. The students are expected to gain a foundational understanding in machine learning. The students, moreover, will be expected to gain hand-on experience via a term project.
The course is taught by Dr. Ahmet Selman Bozkır.
First Midterm: 14.4.2023 - Friday at 19:40 (Online)
Second Midterm: 26.5.2023 - Friday at 19:00
Final: Will be announced - Friday at 18:40
Lectures: Friday at 18:30-20:30 (Online)
Policies: All work on project must be done individually unless stated otherwise. You are encouraged to discuss with your classmates about the given project, but these discussions should be carried out in an abstract way. That is, discussions related to a particular solution to a specific problem (either in actual code or in the pseudocode) will not be tolerated.
In short, turning in someone else’s work, in whole or in part, as your own will be considered as a violation of academic integrity. The conducted study must be reported in a suitable format and be sent through email.
The course webpage will be updated regularly throughout the semester with lecture notes, presentations, and important deadlines. Since this class wil be taught online, it is obligatory to register Piazza VBM686 communication group
Grading for VBM686 will be based on
Date | Topic | Notes |
Mar 3 | Introduction [slides] | Welcome, Introduction to Computer Vision, General Concepts |
Mar 10 | Image Acquasition [slides] | In Camera Pipeline, White Balancing, Color, Denoising, RAW Imaging |
Mar 17 | Image Filtering [slides] | Image Filtering,Filter Types, Convolution, Correlation, Image Gradients, LoG and DoG |
Mar 24 | Bilateral Filtering [slides] | Bilateral Filtering, Flash/No Flash Photography |
Mar 31 | Guided Image Filtering [slides] | Guided Image Filtering with Examples |
Apr 7 | Color Spaces and Features [slides] | Color Spaces, Global Image Features, Histogram Representations |
Apr 14 | 1st Midterm | No class |
Apr 21 | Official Holiday | No class |
Apr 28 | Local Features: SIFT [slides] | SIFT Features, Scale Space, Use of DOG, Image Matching |
May 5-12 | Convolutional Neural Networks [slides] | MLP, CNNs, Fully Convolutional Networks, Parameter Computatation, Applications |