EGE UNIVERSITY

GRADUATE SCHOOL OF NATURAL AND APPLIED SCIENCES
ENGINEERING SCIENCES

COMPUTER ENGINEERING DEPARTMENT

 

 

 

 

2018-2019 FALL SEMESTER

 

 

 

 

Course

 

 

529 DIGITAL IMAGE PROCESSING (3+0)

 

 

Instructor

 

 

Prof. Dr. Aybars UĞUR

 

Course Place and Time

 

 

Sun Lab. in EGE University Computer Engineering Department

Monday 13:15-16:00

 

 

Learning Outcomes

 

 

 

1-To learn basic concepts of Digital Image Processing (DIP), mathematical and software background; to have ability to apply DIP to problems. To recognize the role of DIP in computer engineering and computer science.

 

2-To develop Image Processing Software; To have ability to apply segmentation, image analysis and recognition techniques on images in real life.

 

3-To introduce and to learn ability to use the Image Processing Platforms and Tools like Matlab, Python, OpenCV and Aforge.NET.

 

4-To do research in state-of-the-art subjects of digital image processing area; preparing and doing presentation. To gain experience in reading and writing papers in DIP.

 

 

Description

 

Fundamentals of Image Processing and MATLAB & Python, Intensity Transformations and Spatial Filtering, Frequency Domain Processing, Image Restoration, Quantization, Color Image Processing, Wavelets and Multi-Resolution Processing, Image Compression, Morphological Image Processing, Image Segmentation, Representation and Description, Object Recognition.

 

 

Textbook

 

Gonzalez, R.C., Woods, R., “Sayısal Görüntü İşleme”, 3. baskının çevirisi, Palme Yayıncılık, 2014. Çevirmenler: Fikret Arıt, Ziya Telatar, Hakan Tora, Aykut Kalaycıoğlu

Gonzalez, R.C., Woods, R., “Digital Image Processing, 3rd Edition, Prentice-Hall, (2008).

 

Reference Books

 

  • OpenCv Görüntü İşleme ve Yapay Öğrenme”, Birol Kuyumcu, Level Kitap, 2015.
  • Image Processing. Analysis and Machine Vision” (Fourth Edition), Milan Sonka, Vaclav Hlavac, Roger Boyle, Cengage Learning, 2014.
  • Digital Image Processing Using Matlab”, 2nd Edition, by R. Gonzalez, R. Woods and S. Eddins, 2009, Prentice Hall.

 

 

Prerequisites

 

Artificial Intelligence Background, basic knowledge of probability, linear algebra, and calculus. MATLAB programming experience and previous exposure to image processing are desirable, but not required.

 

 

Grading

 

Mid-term Activities (60%)

Project 1 (10%)

Take-Home (25%)

Presentation (10%)

Term Project + Paper (15%)

 

For the projects (programming assignments), students will be allowed a total of 5 (five) late days; each additional late day will incur a 10% penalty.

  

Final Exam (40%)