ECOE 508-Computer Vision

Spring 2008

Computer Engineering Department, Koç University

 Dr. Yücel Yemez

 

Office: Eng139   Phone: (0212) 338 1585

E-mail: yyemez@ku.edu.tr

Tuesday & Thursday 12:30-13:45, Eng-B05

 

 

Syllabus

Assignments

Projects

Course flow

Links

 


 

Course Description

ECOE 508 is a graduate course to introduce the fundamentals of computer vision theory and practice. With recent developments in computing, transmission and display technologies,  2D/3D visual data are becoming more commonplace in scientific, industrial and commercial arenas. The digital visual data are mostly reflections from real world and contain useful information. The main goal of computer vision is to analyze sensed images for extracting this information, to construct scene descriptions and knowledge representations, to recognize objects and thereby to make useful decisions about physical objects and scenes.

The course is open to graduate students who are willing to understand the vision technology in conjunction with real world applications and especially very well suited to those who are interested in doing research in computer vision. Good programming skills and knowledge of C/C++ are necessary for the course project and homework assignments. Basic DSP knowledge will also be very helpful.

Syllabus (in pdf)

Textbook

M. Sonka, V. Hlavac and R. Boyle, Image Processing, Analysis, and Machine Vision, Thomson-Engineering, 1998.

 

Reference books

Shapiro and Stockman, Computer Vision, Prentice Hall, 2001.

E. Trucco and A. Verri, Introductory Techniques for 3-D Computer Vision, , Prentice Hall, 1998.

Honor Code

All code and documentation handed in exams, assignments and projects must be your own work. In programming assignments, you can exchange ideas, but you should not ever share your code, even partly.

Grading

Final grades will be composed of: (tentative)

Programming assignments

30%

Exam

30%

Project

40%

 


 

Programming assignments

There will be programming assignments posted here. All code must be written either in C/C++ using OpenCV libraries or Matlab Image Processing Toolbox. Source code documentation and organization should make your programs easy to read and convey your understanding of the implemented applications. Poor documentation and programming style will result in a lower score.

 


 

Projects

By the first month of the semester, each student will have chosen a topic for her/his project. Projects can be either research oriented or applications programming oriented, addressing one of the computer vision problems/concepts/applications covered throughout the course. Depending on the chosen topic, students may be expected to do a literature survey on different techniques aiming at solving the specified problem and then to implement and test one of these techniques. A software implementation is mandatory, using C/C++/OpenCV or Matlab.

Students are expected to submit a project proposal by April 15.

 


 

Lecture Notes

Lecture Topic Reading
Feb 7 Imaging Chapters 1 and 2
Feb 12-21 Filtering & Enhancement Chapter 3, Chapter 5.1, 5.2
Feb 26-28 Fetaure Detection Chapter 5.3, Chapter 3.2
March 4,6,11,13 Pattern Recognition Concepts Chapters 8 and 9
March 18,20 PCA & LDA  See supplementary notes
March 25 Texture Chapter 15
March 27 Image retrieval Shapiro/Chapter 8
April 1,3,15 Segmentation Chapter 5
April 22,24, May 6 3D Vision Chapters 9,10
May 8 Binary Morphology Chapter 11.1-11.5

 

Supplementary reading that may be helpful:

Support Vector Machines

PCA vs LDA

 

Segmentation as graph partitioning

 

Exam Date: 13 May, Tuesday, Class hours

 

Project Presentations: 28 May, Thursday, 13:30-15:30


 

Some Useful Links

 

OpenCV Resources

 

Utility Software