ELECTRIC-ELECTRONIC ENGINEERING (ENGLISH, PHD) | |||||
PhD | TR-NQF-HE: Level 8 | QF-EHEA: Third Cycle | EQF-LLL: Level 8 |
Course Code | Course Name | Semester | Theoretical | Practical | Credit | ECTS |
EEE5550 | Computer Vision and Pattern Recognition | Fall | 3 | 0 | 3 | 12 |
This catalog is for information purposes. Course status is determined by the relevant department at the beginning of semester. |
Language of instruction: | English |
Type of course: | Departmental Elective |
Course Level: | |
Mode of Delivery: | Face to face |
Course Coordinator : | Dr. Öğr. Üyesi ZAFER İŞCAN |
Recommended Optional Program Components: | None |
Course Objectives: | The aim of the course is to study computer vision, which tries to “make computers see and interpret” using the observations in the form of multiple 2D (or 3D) images. In this undergraduate/graduate level course, the focus is on mainly basic computer vision concepts. 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 computer vision, its uses and applications 2.Design various point-wise intensity transformations, neighborhood and spatial filtering operations over images 3.Transform images by geometric transforms: rigid, affine, and polynomial warping 4. Define and compute feature extraction operators: edges and corners, lines, and scale-invariant feature extraction in images 5. Describe mathematical image morphological operators 6. Construct segmentation algorithms: histogram-analysis-based thresholding, clustering intensities, and region growing 7. Discuss visual motion estimation methods 8. Apply object and shape recognition approaches to problems in computer vision 9. Describe basic multiple view geometry and stereo concepts |
Introduction to Computer Vision, Human Visual System, Pointwise Operations, Intensity Transformations, Histograms, Enhancement, Spatial Filtering, Neighborhood Operations, Edge Detection, Feature Extraction: Corners, Hough, Ellipse Fit, RANSAC, Correlation, SIFT, SURF, Morphological Image Processing, Segmentation: Adaptive Thresholding, Otsu, Region Growing, Active Contours, Segmentation: Adaptive Thresholding, Otsu, Region Growing, Active Contours, Introduction to Pattern Recognition, Review of Probability, Bayesian Decision Theory, Bayesian Estimation, PCA, kNN, SVM, Camera models, Camera Calibration, Stereopsis, Motion Estimation, Tracking |
Week | Subject | Related Preparation |
2) | Spatial Filtering Neighborhood Operations Edge Detection | |
3) | Feature Extraction: Corners, Hough, Ellipse Fit, RANSAC, Correlation | |
4) | Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF) | |
5) | Morphological Image Processing | |
6) | Segmentation: Adaptive Thresholding, Otsu, Region Growing, Active Contours | |
7) | Review, midterm exam | |
8) | Introduction to Pattern Recognition Review of Probability | |
9) | Bayesian Decision Theory | |
10) | Bayesian Estimation, PCA, kNN, SVM | |
11) | Camera models, Camera Calibration | |
12) | Stereopsis | |
13) | Motion Estimation | |
14) | Tracking |
Course Notes / Textbooks: | Computer Vision: A Modern Approach (2nd Edition), David A. Forsyth and Jean Ponce, Prentice Hall, 2011. Digital Image Processing, R.C. Gonzalez, R.E. Woods, Pearson Prentice Hall 2008. |
References: | Computer Vision, D. Ballard and C.M. Brown, Prentice Hall, online at: http://homepages.inf.ed.ac.uk/rbf/BOOKS/BANDB/bandb.htm |
Semester Requirements | Number of Activities | Level of Contribution |
Homework Assignments | 4 | % 10 |
Project | 1 | % 25 |
Midterms | 1 | % 25 |
Final | 1 | % 40 |
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 |
Study Hours Out of Class | 14 | 4 | 56 |
Project | 1 | 15 | 15 |
Homework Assignments | 4 | 20 | 80 |
Midterms | 1 | 3 | 3 |
Final | 1 | 3 | 3 |
Total Workload | 199 |
No Effect | 1 Lowest | 2 Low | 3 Average | 4 High | 5 Highest |
Program Outcomes | Level of Contribution |