Computer Vision is the science and technology of giving computers the ability to “see” and “understand” images taken by one or more cameras. The goal of this course is to study and develop algorithms for interpreting the visual world captured in images or videos. The course is divided into four parts: The first part gives a general introduction. It discusses the research frontiers in computer vision by showing some state-of-the-art applications (e.g., detection and recognition, automated visual inspection, 3D reconstruction and image stitching). The second part explains the basics of how to deal with digital images. It includes image formation, image acquisition, image processing (enhancement, filtering, morphological operations, edge detection and segmentation) and video processing (optical flow and tracking). The third part focuses on automatic recognition of patterns. It covers feature extraction and selection, local descriptors and classification algorithms. Finally, the fourth part treats geometric vision topics. It consists of projective geometry, camera geometric model, camera calibration, stereovision and 3D reconstruction. With this course the students will be able to understand computer vision literature, recognize the frontiers of state-of-the-art computer vision systems and develop algorithms that are essential to many modern systems in this field. Projects in the course will utilize a high level programming language (preferably Matlab, but other languages like OpenCV, Python or C++ will be allowed also).
Professor Mery will be holding additional office hours every Friday, immediately after lecture, from 11:30am - 12:30pm. 355C Fitzpatrick Hall.
No required textbooks, however these textbooks are suggested:
- R. Szeliski (2010): Computer Vision: Algorithms and Applications, Springer. [ PDF ]
- K. Reinhard (2014): Concise Computer Vision. Springer.
- D.A. Forsyth, J. Ponce (2002): Computer Vision: A Modern Approach, Prentice Hall.
- R. Gonzalez, R. Woods, S. Eddins (2009): Digital Image Processing Using MATLAB, 2nd edition. Gatesmark Publishing.
- R.O. Duda, P.E. Hart, and D.G. Stork (2000): Pattern Classification. 2nd Edition. Wiley-Interscience. [ PDF ]
- R. Hartley, A. Zisserman (2004): Multiple View Geometry in Computer Vision, 2nd Edition.Cambridge University Press. [ PDF1 ] [ PDF2 ]
Assignments & Project
As members of the Notre Dame University, we will not participate in or tolerate academic dishonesty. See more details of the ND Honor Code here.
You may consult any books, papers, webpages, etc. for ideas and available codes that you may want to incorporate into your implementation, so long as you clearly cite your sources. However, under no circumstances may you look or use someone else's work as if it were your own. If you aren’t sure whether a certain form of collaboration is allowed, you should consult with the instructor.
10% Class participation
Attendance is not mandatory, however, you are expected to attend and participate in the lectures. Discussion is a key aspect of learning; class particpation is expected and will be tracked as part of your grade.