COURSE SYLLABUS

COMPUTER VISION

1	Course Title:	COMPUTER VISION
2	Course Code:	BM5113
3	Type of Course:	Optional
4	Level of Course:	Second Cycle
5	Year of Study:	1
6	Semester:	1
7	ECTS Credits Allocated:	6
8	Theoretical (hour/week):	3
9	Practice (hour/week) :	0
10	Laboratory (hour/week) :	0
11	Prerequisites:	None
12	Recommended optional programme components:	None
13	Language:	Turkish
14	Mode of Delivery:	Face to face
15	Course Coordinator:	Dr. Ögr. Üyesi CEYDA NUR ÖZTÜRK
16	Course Lecturers:
17	Contactinformation of the Course Coordinator:	ceydanur@uludag.edu.tr
18	Website:
19	Objective of the Course:	To introduce matching, classification, detection, segmentation, registration, tracking, and reconstruction-like problems that should be solved to provide computers with ability to see and to examine necessary representations, techniques, and algorithms for solution of these problems.
20	Contribution of the Course to Professional Development	Develops skills to use proper methods for understanding information that is asked for in various images and hence to manage the visual perception tasks of high-level intelligent systems.

Learning Outcomes:

1	Being able to describe the relationships between camera images and physical world;
2	Being able to extract image features and produce descriptors for them;
3	Being able to obtain foreground and flow information in moving images;
4	Being able to classify and segment objects of interest in images;
5	Being able to provide alignment between source and destination images;
6	Knowing the approaches of depth estimation from images;
7	Being able to use convolutional neural networks for some vision problems;

22	Course Content:

Week	Theoretical	Practical
1	Overview of computer vision problems, image formation
2	Fundamental image processing: intensity transformations, noise types, linear and nonlinear filtering
3	Fundamental image processing: histograms, edge detection, morphological operations
4	Image features: edge, corner, line, and circle detection, template matching
5	Interest point detectors and descriptors: SIFT, SURF, ORB, HOG, LBP algorithms, spatiotemporal interest points
6	Transforms: Hough, Fourier, Haar and wavelet transforms
7	Alignment: geometric transformations, point matching, image warping, homography estimation and RANSAC algorithm
8	Moving image processing: background subtraction and optical flow
9	Camera parameters, perspective projection, camera calibration
10	Stereo vision and epipolar geometry, sparse and dense depth maps, 3-D reconstruction
11	Object detection and segmentation: texture and shape modelling, classification, clustering, and registration approaches
12	Object tracking in moving images: Lucas-Kanade, mean shift, MOSSE and KCF algorithms
13	Convolutional neural networks: convolution layers, pooling layers, and fully connected layers, various architectures
14	Classification, detection, and segmentation of objects with convolutional neural networks

23	Textbooks, References and/or Other Materials:	1. Szeliski, R., 2010. Computer Vision: Algorithms and Applications, Springer Science & Business Media, ISBN: 978-1848829343. 2. Dadhich, A., 2018. Practical Computer Vision: Extract Insightful Information from Images Using TensorFlow, Keras, and OpenCV. Packt Publishing, ISBN: 978-1788297684.
24	Assesment

TERM LEARNING ACTIVITIES	NUMBER	PERCENT
Midterm Exam	0	0
Quiz	0	0
Homeworks, Performances	3	60
Final Exam	1	40
Total	4	100
Contribution of Term (Year) Learning Activities to Success Grade		60
Contribution of Final Exam to Success Grade		40
Total		100
Measurement and Evaluation Techniques Used in the Course	Programming assignments, project, presentation, written exam
Information

ECTS / WORK LOAD TABLE

CONTRIBUTION OF LEARNING OUTCOMES TO PROGRAMME QUALIFICATIONS

LO: Learning Objectives

PQ: Program Qualifications

Contribution Level:

1 Very Low

2 Low

3 Medium

4 High

5 Very High