Computer Vision (EE573) Course Detail

Course Name Course Code Season Lecture Hours Application Hours Lab Hours Credit ECTS
Computer Vision EE573 3 0 0 3 5
Pre-requisite Course(s)
Math 158, Math 275, EE 204
Course Language English
Course Type N/A
Course Level Natural & Applied Sciences Master's Degree
Mode of Delivery Face To Face
Learning and Teaching Strategies Lecture, Drill and Practice.
Course Coordinator
Course Lecturer(s)
  • Asst. Prof. Dr. Hakan Tora
  • Asst. Prof. Dr. Hakan Tora
Course Assistants
Course Objectives • Study the fundamental problems of computer vision • Study the fundamental concepts and techniques used to solve problems in computer vision • Study typical application domains where computer vision and video electronics are used
Course Learning Outcomes The students who succeeded in this course;
  • Ability to apply the algorithms and techniques in the literature for solving low-level, mid-level and high-level vision problems
  • Ability to acquire images with single or multiple cameras
  • Ability to infer 3D structure information from images, infer motion contents from image sequences, detect and recognize objects of interest
  • Ability to write programs that can perform image segmentation, image matching, object detection or recognition
  • Ability to have hands-on experience in developing algorithms and systems in term projects
Course Content Human vision, geometric camera models, image segmentation, object recognition, video signals and standards, vision system design, computer vision and digital video applications.

Weekly Subjects and Releated Preparation Studies

Week Subjects Preparation
1 Introduction: Fundamentals of imaging, The Physics of Imaging Glance this week’s topics from the lecture
2 Images and Imaging Operations: Image processing operations and image filtering operations Glance this week’s topics from the lecture
3 Images and Imaging Operations Review last week and glance this week’s topics from the lecture
4 Image Segmentation: Clustering methods, fitting a model Glance this week’s topics from the lecture
5 Image Segmentation Review last week and glance this week’s topics from the lecture
6 Introduction to Recognition: Model of pattern classification, statistical techniques for classification Glance this week’s topics from the lecture
7 Introduction to Recognition Review last week and glance this week’s topics from the lecture
8 Geometric Camera Models: Camera parameters and the perspective projection, affine cameras, camera calibration Glance this week’s topics from the lecture
9 Geometric Camera Models Review last week and glance this week’s topics from the lecture
10 Video Signals and Standards: Introduction to digital video, image and video compression and decompression Glance this week’s topics from the lecture
11 Video Signals and Standards Review last week and glance this week’s topics from the lecture
12 Vision System Design: Cameras and Digitization, Real time hardware and systems design considerations , Basic ideas on optimal hardware implementations Glance this week’s topics from the lecture
13 Applications: Automated visual inspection, biometrics, robotics, people tracking, video surveillance, human-computer interaction Glance this week’s topics from the lecture
14 Applications Review last week and glance this week’s topics from the lecture
15 Final Examination period Review of topics
16 Final Examination period Review of topics

Sources

Course Book 1. Computer Vision: A Modern Approach, David A. Forsyth and Jean Ponce, Prentice Hall, 2003
Other Sources 2. Machine vision: theory, algorithms, practicalities, Davies, E. R. (E. Roy), Elsevier, 2005

Evaluation System

Requirements Number Percentage of Grade
Attendance/Participation - -
Laboratory - -
Application 8 15
Field Work - -
Special Course Internship - -
Quizzes/Studio Critics - -
Homework Assignments 15 10
Presentation - -
Project 1 25
Report - -
Seminar - -
Midterms Exams/Midterms Jury 1 20
Final Exam/Final Jury 1 30
Toplam 26 100
Percentage of Semester Work 70
Percentage of Final Work 30
Total 100

Course Category

Core Courses X
Major Area Courses
Supportive Courses
Media and Managment Skills Courses
Transferable Skill Courses

The Relation Between Course Learning Competencies and Program Qualifications

# Program Qualifications / Competencies Level of Contribution
1 2 3 4 5
1 Ability to apply knowledge on Mathematics, Science and Engineering to advanced systems.
2 Implementing long-term research and development studies in major areas of Electrical and Electronics Engineering.
3 Ability to use modern engineering tools, techniques and facilities in design and other engineering applications.
4 Graduating researchers active on innovation and entrepreneurship.
5 Ability to report and present research results effectively.
6 Increasing the performance on accessing information resources and on following recent developments in science and technology.
7 An understanding of professional and ethical responsibility.
8 Increasing the performance on effective communications in both Turkish and English.
9 Increasing the performance on project management.
10 Ability to work successfully at project teams in interdisciplinary fields.

ECTS/Workload Table

Activities Number Duration (Hours) Total Workload
Course Hours (Including Exam Week: 16 x Total Hours) 16 3 48
Laboratory
Application
Special Course Internship
Field Work
Study Hours Out of Class 16 3 48
Presentation/Seminar Prepration 1 4 4
Project 5 3 15
Report
Homework Assignments 5 2 10
Quizzes/Studio Critics
Prepration of Midterm Exams/Midterm Jury 2 2 4
Prepration of Final Exams/Final Jury 1 2 2
Total Workload 131