Iğdır University Lifelong Learning Programme

Description of Individual Course Units

Course Unit Code	Course Unit Title	Type of Course Unit	Year of Study	Semester	Number of ECTS Credits
190105000111	FUNDAMENTALS OF IMAGE PROCESSING	Elective	4	7	6

Level of Course Unit

First Cycle

Objectives of the Course

Image Processing course aims to teach the basic concepts and current techniques used in the processing, analysis and interpretation of digital images. Within the scope of this course, students learn basic image processing topics such as image enhancement, restoration, compression, segmentation and recognition both theoretically and practically and gain the ability to develop solutions to problems they may encounter in real life.

Name of Lecturer(s)

Dr. Öğr. Üyesi Fesih Keskin

Learning Outcomes

1	Explains the fundamental concepts and methods of image processing.
2	Applies various image processing techniques to solve real-world problems.
3	Develops image analysis and visual data processing projects using Python and relevant libraries.
4	Utilizes advanced techniques such as image segmentation, texture analysis, and object recognition.
5	Integrates machine learning and deep learning methods into image processing applications.

Mode of Delivery

Daytime Class

Prerequisites and co-requisities

None

Recommended Optional Programme Components

None

Course Contents

Fundamentals of Image Processing course covers basic and current techniques for processing, analyzing and interpreting digital images. The course covers the definition of digital images, image acquisition methods, camera and sensor systems, medical imaging devices, Python programming language and image processing libraries (NumPy, OpenCV, etc.). In addition, point and area-based operations such as brightness and contrast adjustment, thresholding, histogram operations, spatial and frequency domain filtering, noise removal and sharpening are covered. Binary image analysis, morphological operations, shape descriptors, color image analysis and segmentation methods (K-means, fuzzy C-means, level sets, etc.) are also important topics of the course. In addition, advanced topics such as texture analysis, salient point detection (SIFT, SURF, ORB), visual vocabulary modeling and feature extraction are covered. Finally, the fundamentals of machine learning and deep learning, modern approaches such as image recognition and object detection models are examined, enabling students to reinforce their theoretical knowledge with practical projects.

Weekly Detailed Course Contents

Week	Theoretical	Practice	Laboratory
1	Introduction to Image Processing: Definition of digital images, overview of image processing, application areas, basic concepts, course outline, and requirements.
2	Image Acquisition and Medical Image Sources: Principles of image formation, camera and sensor structures, medical imaging devices, image characteristics, basic hardware, and software components.
3	Introduction to Python: Basics of Python programming, image processing libraries (NumPy, OpenCV, etc.), basic data structures, and function usage.
4	Point Operations: Brightness and contrast adjustment, thresholding methods, histogram and histogram equalization.
5	Filters: Spatial filtering (mean, Gaussian, median filters), basics of frequency domain filtering, noise reduction, and sharpening techniques.
6	Binary Image Analysis: Methods of creating binary images, morphological operations (erosion, dilation, opening, closing), basic feature extraction.
7	Binary Image Descriptions and Color Image Analysis: Shape descriptors (area, perimeter, shape factors), color models (RGB, HSV, etc.), color separation and segmentation.
8	Midterm Exam: Assessment of the topics covered so far.
9	Segmentation: Methods such as K-means, Fuzzy C-means, level sets; edge-based and region-based segmentation approaches; real-world segmentation challenges.
10	Texture Analysis: Concept of texture, statistical properties, filter-based texture analysis techniques (Gabor, LBP, etc.), practical examples, and evaluation.
11	Keypoints: Detection of keypoints (SIFT, SURF, ORB, etc.), matching keypoints and object recognition, practical examples.
12	Visual Words: Feature vectors and feature extraction, “Bag of Visual Words” model, classification, and clustering.
13	Modeling: Basic concepts of machine learning and deep learning, fundamentals of image recognition and object detection models, current research topics, and applications.
14	General Review: Comprehensive review of the topics covered throughout the semester and Q&A session.
15	Final Exam: Evaluation of students’ theoretical knowledge and practical skills.
16	Final Exam: Comprehensive assessment and presentation of end-of-term projects.