MATHEMATICS (TURKISH, PHD) | |||||
PhD | TR-NQF-HE: Level 8 | QF-EHEA: Third Cycle | EQF-LLL: Level 8 |
Course Code | Course Name | Semester | Theoretical | Practical | Credit | ECTS |
EEE6531 | Image Understanding | Fall | 3 | 0 | 3 | 12 |
The course opens with the approval of the Department at the beginning of each semester |
Language of instruction: | En |
Type of course: | Departmental Elective |
Course Level: | |
Mode of Delivery: | Face to face |
Course Coordinator : | Dr. Öğr. Üyesi ZAFER İŞCAN |
Course Objectives: | The aim of the course is to study advanced image processing computer vision concepts, which tries to “make computers see and interpret” using the observations in the form of multiple 2D (or 3D) images and video. The course will provide the participants with a background in computer vision both in practical aspects as being able to implement computer vision algorithms, and their mathematical understanding. |
The students who have succeeded in this course; 1. Discuss the main problems of advanced computer vision, its uses and applications 2. Design various advanced feature extraction methods. 3.Describe advanced segmentation approaches involving e.g. markov random fields, graph based methods. 4.Define and compute structure from motion using direct methods 5.Describe structure from motion using factorization 6.Discuss multibody motion segmentation algorithms 7.Discuss shape from shading 8.Apply stereo vision principles 9.Describe 2D object recognition approaches 10.Design face recognition algorithms |
Extraction of optimal Edge, Shape and Skeleton Features. Hough Transform, Segmentation 1 - Markov Random Fields, Filtering Methods, Graph based Methods, Overview of Camera Models, Calibration and Optimization Theory, MRF and Simulated Annealing, Particle Filters/Sequential Important Sampling (SIS), PF Methods for Tracking, Structure From Motion - Early approaches, Structure From Motion - Filtering based approaches, Optical Flow estimation, Factorization, Multibody motion segmentation, Shape from Shading, Stereo Vision, 2D object recognition, Face Recognition |
Week | Subject | Related Preparation | |
1) | Extraction of optimal Edge, Shape and Skeleton Features. Hough Transform. | ||
2) | Segmentation - Markov Random Fields, Filtering Methods, Graph based Methods | ||
3) | Overview of Camera Models, Calibration and Optimization Theory | ||
4) | MRF and Simulated Annealing | ||
5) | Particle Filters/Sequential Important Sampling (SIS) | ||
6) | PF Methods for Tracking | ||
8) | Structure From Motion 1- Early approaches | ||
10) | Multibody motion segmentation | ||
11) | Shape from Shading | ||
12) | Stereo Vision | ||
13) | 2D object recognition | ||
14) | Face Recognition |
Course Notes: | Research papers Computer Vision: A Modern Approach (2nd Edition), David A. Forsyth and Jean Ponce, Prentice Hall, 2011. |
References: | Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, 2011. |
Semester Requirements | Number of Activities | Level of Contribution |
Attendance | % 0 | |
Laboratory | % 0 | |
Application | % 0 | |
Field Work | % 0 | |
Special Course Internship (Work Placement) | % 0 | |
Quizzes | % 0 | |
Homework Assignments | 3 | % 10 |
Presentation | % 0 | |
Project | 1 | % 25 |
Seminar | % 0 | |
Midterms | 1 | % 25 |
Preliminary Jury | % 0 | |
Final | 1 | % 40 |
Paper Submission | % 0 | |
Jury | % 0 | |
Bütünleme | % 0 | |
Total | % 100 | |
PERCENTAGE OF SEMESTER WORK | % 35 | |
PERCENTAGE OF FINAL WORK | % 65 | |
Total | % 100 |
Activities | Number of Activities | Duration (Hours) | Workload |
Course Hours | 14 | 3 | 42 |
Laboratory | 0 | 0 | 0 |
Application | 0 | 0 | 0 |
Special Course Internship (Work Placement) | 0 | 0 | 0 |
Field Work | 0 | 0 | 0 |
Study Hours Out of Class | 14 | 4 | 56 |
Presentations / Seminar | 0 | 0 | 0 |
Project | 1 | 15 | 15 |
Homework Assignments | 3 | 10 | 30 |
Quizzes | 0 | 0 | 0 |
Preliminary Jury | 0 | 0 | 0 |
Midterms | 1 | 3 | 3 |
Paper Submission | 0 | 0 | 0 |
Jury | 0 | 0 | 0 |
Final | 1 | 3 | 3 |
Total Workload | 149 |
No Effect | 1 Lowest | 2 Low | 3 Average | 4 High | 5 Highest |
Program Outcomes | Level of Contribution |