[MKT6121 Image Processing] Syllabus

[2023-Spring]

Instructor Info:
Instructor E-Posta Address
[Ertuğrul BAYRAKTAR] [[email protected]] [Building E, Room No: 221]

General Information
Description
Lecturing plan for the course of MKT6121 Image Processing taught in the Department of Mechatronics Engineering at
Yildiz Technical University.

Microsoft Teams Channel

https://teams.microsoft.com/l/team/19%3aRcpS8ObBcXUg6SeqVVW8BaoQkkXOHBnRwiNeIZ3h8G01%40thread.tacv2/
conversations?groupId=4e26be1b-9c8a-43e8-8675-7ac3103f9e26&tenantId=85602908-e15b-43ba-9148-
38bc773a816e

Objectives
- To examine image processing and computer vision algorithms for industrial machine vision applications
- To discuss the theory and practical applications of machine vision
- To give knowledge on mathematical concepts and techniques
- To translate these techniques into the appropriate programming language for the solution of real problems in
the industry.
- To consolidate the knowledge given by quizzes and assignments

Material
Recommended Or Required Reading
Fundamentals Of Digital Image Processing, Annadurai
Digital Image Processing, Rafael C. González, Richard Eugene Woods
Machine Vision Handbook, Bruce G. Batchelor
Computer Vision: Algorithms and Applications, 2nd ed., Richard Szeliski
Multiple View Geometry in Computer Vision, Richard Hartley and Andrew Zisserman

Page 1
Weekly Subjects and Related Preparation Studies
Week Subjects Related Preparation

1 Introduction to image processing; fundamentals and image Examination of the section on reference book.
formation, pinhole camera model, Color spaces and color
thresholding

2 Spatial filtering, and histogram processing Examination of the section on reference book.

3 Sampling, quantization, and frequency domain image Examination of the section on reference book.
filtering

4 Edge and corner detection Examination of the section on reference book.

5 Feature extraction and matching Examination of the section on reference book.

6 Feature extraction and matching Examination of the section on reference book.

7 Object classification and detection Examination of the section on reference book.

8 Midterm Exam Examination of the section on reference book.

9 Geometric transformations and single view geometry Examination of the section on reference book.

10 Stereo vision, epipolar geometry and the fundamental matrix Examination of the section on reference book.

11 Morphological image processing and segmentation Examination of the section on reference book.

12 Structure From Motion, Optical flow Examination of the section on reference book.

13 Object Tracking, Visual SLAM Examination of the section on reference book.

14 Project Presentation Examination of the section on reference book.

Exam Schedule
Date Subject

M1

Project

Final

Page 2
Additional Information
Course Learning Outcomes
1. Describe image representations
2. Apply spatial filtering transformations
3. Apply frequency filtering transformations
4. Perform image restoration and reconstruction techniques
5. Describe image compression
6. Perform image segmentation
7. Describe image descriptors
8. Perform pattern recognition on a mechatronics application
9. Specify an industrial problem related to machine vision and develop consistent solution

Grading Policy:
- Evaluation Tools Through Semester: 60%
- Final Evaluation Tool: 40%

Projects:
- Groups should be 2-member teams. The division of labour and contribution of each team member must be
specified explicitly. The projects cannot be taken directly from existing and same-content works.
- The project proposal should be one paragraph (200-400 words). Your project proposal should describe:
o What is the problem that you will be investigating? Why is it interesting?
o What reading will you examine to provide context and background?
o What data will you use? If you are collecting new data, how will you do it?
o What method or algorithm are you proposing? If there are existing implementations, will you use
them and how? How do you plan to improve or modify such implementations? You don't have to
have an exact answer at this point, but you should have a general sense of how you will approach the
problem you are working on.
o How will you evaluate your results? Qualitatively, what kind of results do you expect (e.g. plots or
figures)? Quantitatively, what kind of analysis will you use to evaluate and/or compare your results
(e.g. what performance metrics or statistical tests)?
o Submission: Please submit your proposal as a PDF on MS Teams. Only one person on your team
should submit. Please have this person add the rest of your team as collaborators as a "Group
Submission".
Your final write-up is required to be between 6 - 8 pages using the provided template (you can access via MS Teams).
The final phase of project reports in addition to a detailed README.txt file, which describes what processes must be
performed to run your code without errors, should be in the following form:
Title, Author(s)
Abstract: Briefly describe your problem, approach, and key results. Should be no more than 300 words.
Introduction (10%): Describe the problem you are working on, why it's important, and an overview of your results
Related Work (10%): Discuss published work that relates to your project. How is your approach similar or different
from others?
Data (10%): Describe the data you are working with for your project. What type of data is it? Where did it come from?
How much data are you working with? Did you have to do any preprocessing, filtering, or other special treatment to
use this data in your project?
Methods (30%): Discuss your approach for solving the problems that you set up in the introduction. Why is your
approach the right thing to do? Did you consider alternative approaches? You should demonstrate that you have
applied ideas and skills built up during the quarter to tackling your problem of choice. It may be helpful to include
figures, diagrams, or tables to describe your method or compare it with other methods.

Page 3
Experiments (30%): Discuss the experiments that you performed to demonstrate that your approach solves the
problem. The exact experiments will vary depending on the project, but you might compare with previously published
methods, perform an ablation study to determine the impact of various components of your system, experiment with
different hyperparameters or architectural choices, use visualization techniques to gain insight into how your model
works, discuss common failure modes of your model, etc. You should include graphs, tables, or other figures to
illustrate your experimental results.
Conclusion (5%) Summarize your key results - what have you learned? Suggest ideas for future extensions or new
applications of your ideas.
Writing / Formatting (5%) Is your paper clearly written and nicely formatted?

You can benefit from similar courses’ projects and project ideas/approaches (https://cs230.stanford.edu/project/,
http://cs231n.stanford.edu/project.html, https://stanford-cs221.github.io/spring2020/#project, etc.) as well as
finding an appropriate data and task from kaggle.com or another benchmarking competition.

Deadlines:

• 3rd Week just before the class starts: Project proposals. The expected content for project proposal is written at the
Home Page of MS Teams Class.
• 4th Week: The feedback to your project proposals. HW1 will be given.
• 5th Week just before the class starts: Project prosals will be updated considering the feedback.
• 6th Week just before the class starts: HW1
• 8th Week: Midterm Exam
• 9th Week: HW2 will be given.
• 12th Week just before the class starts: HW2
• 14th Week during class hours: 10-12min project presentation. If we continue online, you can send an offline video
for your prensentation and we play it during the class hours and ask you necessary questions. If we shift to physical
classes, you will present it in the class for 10-12mins.
• The Friday of 14th Week, the project report and codes will be uploaded.
Note: If one of the project components (proposal, presentation, report and code) is missed/is not delivered, the rest
of them will also be assumed to be not delivered.

Naming Convention for Assignments:

For Homeworks, the name of your submission must be your_student_id_number.zip For example: 19036154.zip (Inside
this, the .pdf with the same name and code with the same name and a readme.txt must exist)
For Projects, only one single member of your group must submit the project related documents and the name of the
submission must be your_group_number.zip (Inside this, there can only be .pdf and .py files with the same name in
addition to readme.txt)

Page 4