Information
Code | CEN468 |
Name | Pattern Recognition |
Term | 2024-2025 Academic Year |
Semester | 8. Semester |
Duration (T+A) | 3-0 (T-A) (17 Week) |
ECTS | 6 ECTS |
National Credit | 3 National Credit |
Teaching Language | İngilizce |
Level | Lisans Dersi |
Type | Normal |
Mode of study | Yüz Yüze Öğretim |
Catalog Information Coordinator | Mehmet SARIGÜL |
Course Instructor |
1 |
Course Goal / Objective
The pattern recognition course aims to develop students' skills in recognizing, classifying and analyzing features in images by providing them with the fundamentals of computer image processing. The course content focuses on basic image processing techniques, feature extraction, classification algorithms and deep learning methods, and aims to provide students with mastery of these subjects through practical experiences and projects.
Course Content
First, we start with basic image processing algorithms. These algorithms include edge detection, intensity transformation, and filtering. Next, feature extraction techniques are discussed, including histogram analysis, vertex and edge detection, and feature vectors extraction. Basic and deep learning algorithms such as k-NN, Naive Bayes, SVM are introduced as classification algorithms and how these algorithms can be used in image classification and recognition problems is examined. Finally, image recognition techniques and tools that students can use in projects and applications, such as libraries such as OpenCV and TensorFlow, are taught with applied examples and practical experiences.
Course Precondition
Having taken the Artificial intelligence systems course
Resources
Pattern Recognition and Machine Learning Christopher M. Bishop · 2006
Notes
Lecture notes
Course Learning Outcomes
Order | Course Learning Outcomes |
---|---|
LO01 | Students know the basic concepts in the field of image processing. |
LO02 | Students know and apply basic image processing algorithms and feature extraction techniques such as edge detection, intensity transformation, filtering. |
LO03 | Students know basic classification algorithms and deep learning methods such as k-NN, Naive Bayes, SVM. |
LO04 | Students know libraries and tools that can be used in image processing and pattern recognition projects. |
Relation with Program Learning Outcome
Order | Type | Program Learning Outcomes | Level |
---|---|---|---|
PLO01 | Bilgi - Kuramsal, Olgusal | Has capability in the fields of mathematics, science and computer that form the foundations of engineering | 5 |
PLO02 | Bilgi - Kuramsal, Olgusal | Identifies, formulates, and solves engineering problems, selects and applies appropriate analytical methods and modeling techniques, | 3 |
PLO03 | Bilgi - Kuramsal, Olgusal | Analyzes a system, its component, or process and designs under realistic constraints to meet the desired requirements,gains the ability to apply the methods of modern design accordingly. | |
PLO04 | Bilgi - Kuramsal, Olgusal | Ability to use modern techniques and tools necessary for engineering practice and information technologies effectively. | 3 |
PLO05 | Bilgi - Kuramsal, Olgusal | Ability to design and to conduct experiments, to collect data, to analyze and to interpret results | |
PLO06 | Bilgi - Kuramsal, Olgusal | Has ability to work effectively as an individual and in multi-disciplinary teams, take sresponsibility and builds self-confidence | |
PLO07 | Beceriler - Bilişsel, Uygulamalı | Can access information,gains the ability to do resource research and uses information resources | 4 |
PLO08 | Beceriler - Bilişsel, Uygulamalı | Awareness of the requirement of lifelong learning, to follow developments in science and technology and continuous self-renewal ability | |
PLO09 | Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği | Ability to communicate effectively orally and in writing, and to read and understand technical publications in at least one foreign language | |
PLO10 | Yetkinlikler - Öğrenme Yetkinliği | Professional and ethical responsibility, | |
PLO11 | Yetkinlikler - Öğrenme Yetkinliği | Awareness about project management, workplace practices, employee health, environmental and occupational safety, and the legal implications of engineering applications, | |
PLO12 | Yetkinlikler - Öğrenme Yetkinliği | Becomes aware of universal and social effects of engineering solutions and applications, entrepreneurship and innovation, and knowledge of contemporary issues |
Week Plan
Week | Topic | Preparation | Methods |
---|---|---|---|
1 | What is Image Processing? RGB and Grayscale | What is Image Processing? RGB and Grayscale | Öğretim Yöntemleri: Anlatım |
2 | Image Processing Libraries: Introducing OpenCV Basic Image Processing Operations: Transformations, Scaling, Rotation | Image Processing Libraries: Introducing OpenCV Basic Image Processing Operations: Transformations, Scaling, Rotation | Öğretim Yöntemleri: Anlatım, Gösterip Yaptırma |
3 | Edge Detection Algorithms: Sobel, Canny | Edge Detection Algorithms: Sobel, Canny | Öğretim Yöntemleri: Anlatım |
4 | Image Filtering: Gaussian Filter, Median Filter Applications: Edge Detection and Filtering | Image Filtering: Gaussian Filter, Median Filter Applications: Edge Detection and Filtering | Öğretim Yöntemleri: Anlatım, Gösteri, Gösterip Yaptırma |
5 | Density Transformation and Histogram Analysis | Density Transformation and Histogram Analysis | Öğretim Yöntemleri: Anlatım, Gösteri |
6 | Morphological Processes: Expansion, Erosion, Opening, Closing Applications: Density Transformation and Morphological Operations | Morphological Processes: Expansion, Erosion, Opening, Closing Applications: Density Transformation and Morphological Operations | Öğretim Yöntemleri: Anlatım, Gösteri |
7 | Determining Corners and Edges Hough Transform | Determining Corners and Edges Hough Transform | Öğretim Yöntemleri: Anlatım, Gösterip Yaptırma |
8 | Mid-Term Exam | Ölçme Yöntemleri: Proje / Tasarım |
|
9 | Feature Extraction Methods: HOG, SIFT, SURF Applications: Feature Extraction | Feature Extraction Methods: HOG, SIFT, SURF Applications: Feature Extraction | Öğretim Yöntemleri: Anlatım, Gösterip Yaptırma |
10 | k-NN (Nearest Neighbor) Naive Bayes | k-NN (Nearest Neighbor) Naive Bayes | Öğretim Yöntemleri: Anlatım, Gösterip Yaptırma |
11 | Decision Trees Applications: Basic Classification Algorithms | Decision Trees Applications: Basic Classification Algorithms | Öğretim Yöntemleri: Anlatım, Gösteri |
12 | Artificial neural networks Convolutional Neural Networks (CNN) | Artificial neural networks Convolutional Neural Networks (CNN) | Öğretim Yöntemleri: Anlatım, Gösteri |
13 | Deep Learning Frameworks: TensorFlow, Keras Applications: Deep Learning Based Classification | Deep Learning Frameworks: TensorFlow, Keras Applications: Deep Learning Based Classification | Öğretim Yöntemleri: Anlatım, Gösterip Yaptırma |
14 | Data Collection and Preparation Preprocessing Steps of Image Data | Data Collection and Preparation Preprocessing Steps of Image Data | Öğretim Yöntemleri: Beyin Fırtınası, Tartışma, Anlatım |
15 | Project Presentation and Reporting | Project Presentation and Reporting | Öğretim Yöntemleri: Proje Temelli Öğrenme |
16 | Term Exams | Ölçme Yöntemleri: Yazılı Sınav |
|
17 | Term Exams | Ölçme Yöntemleri: Yazılı Sınav |
Student Workload - ECTS
Works | Number | Time (Hour) | Workload (Hour) |
---|---|---|---|
Course Related Works | |||
Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
Out of Class Study (Preliminary Work, Practice) | 14 | 4 | 56 |
Assesment Related Works | |||
Homeworks, Projects, Others | 1 | 14 | 14 |
Mid-term Exams (Written, Oral, etc.) | 1 | 14 | 14 |
Final Exam | 1 | 28 | 28 |
Total Workload (Hour) | 154 | ||
Total Workload / 25 (h) | 6,16 | ||
ECTS | 6 ECTS |