The fields of computer graphics and computer vision are converging on a set of common models and equations for generating, manipulating, and analyzing images. This course is designed to give students an understanding of these techniques sufficient to pursue graduate research in vision. In particular, students will study image image manipulation (geometric and photometric transformations, image filtering, and morphing), image matching (correlation, principal component analysis, mutual information), object detection and object recognition (including feature extraction, feature transformations, model matching) |
|
The prerequisite for this course is CS 410 .
When appropriate we will be drawing upon material from the book "Computer Vision: Algorithms and Applications" by Richard Szeliski. There is a free electronic version of this textbook available online. In addition, we willbe compiling pointers to appropriate material for each module. These will be referenced from the Progress Page.
Three large programming projects are planned for this course relating to major topics (photorealistic image generation, image manipulation, image matching, and feature extraction & matching). Students are allowed to cooperate with each other, within the guidelines outlined in the Student Information Sheet. Otherwise, unless otherwise clearly stated, all projects are individual projects, not team projects.
Part of the requirement for this class is to write a scholarly paper summarizing some aspect of current research in computer vision and then summarize this paper in a short, perhaps 10 minute, formal presentation in class.
The material covered in this course will be drawn from many sources and the class meetings are important for integrating and elaborating on the different topics being covered. Active participation is a requirement and is expected of all students. Participation will take at least three distinct forms: discussion, short presentations and note taking. Presentations may include explanations of specific problems provided to students in a previous class, live demonstrations of code developed for projects, and summaries of material researched for the term paper.
Note taking, the last of the three activities mentioned, will be explained in more detail in class. In short, each student will be expected to take their turn producing notes on indivdual lectures that will be made publicly available through the course website and beome a part of the formal class record.
The breakdown of how each major requirement counts toward the final grade is summarized in the following table:
Type | Description / Topic Area | Percent of Grade |
Programming Projects | Image Manipulation /Image Matching / Object Recognition | 60 % |
Term Paper | Describe a currently active computer vision area | 10 % |
In Class Participation | Discussion, Short Presentations and Supplemental Notes | 10 % |
Midterm | In class exam | 10 % |
Final | Exam on May 10th 11:50 to 1:50. | 10 % |
Semester grades are determined by the weighted sum of points earned in each of these areas. Total points for each area are normalized so that the best possible score for the semester is 100. Typically the A- to B+ cutoff falls at 90 points, the B- to C+ cutoff at 80 points, and so on. While this is the typical grading procedure, the instructor reserves the right to make adjustments.
Midterm and Final: Make-up exams are only given for extraordinary circumstances (e.g., illness, family emergency). Students must consult with the instructor as soon as possible, preferably before the start of the exam. Course examination dates are listed in the syllabus; be aware of them and plan accordingly.
Projects: Unless otherwise specified, programming assignments are to be submitted electronically through RamCT. Specifics will be included in each assignment. Always check the assignment page for due dates. Late assignments submitted within 48 hours of the time required will receive a 10% late penalty. Electronic submission is closed 48 hours after assignments are due; students not having submitted programs receive an automatic zero on the assignment.
In Class Midterm | March 7th in class |
Final Exam | Thursday, May 10th, 11:50 to 1:50 |
Exam will be held in the same classroom as regular lectures. While no change to the midterm dates is anticipated, the instructor reserves the right to change these dates with a weeks notice.
All students taking this course are expected to participate actively. For all students, includes asking and responding to questions. For distance students, the mechanism for asking and responding to questions is the bulletin board on the RamCT site. The TA will note how many questions you ask! For on-campus students, questions may be asked or answered in class, during office hours, or on the same bulletin board the distance students use.
All students are expected to conduct themselves professionally. We assume you are familiar with the policies in the student information sheet for the department. We further assume you conduct yourself in accordance with the Colorado State University Honor Pledge: I have not given, received, or used any unauthorized assistance. Additionally, you are computing professionals, albeit perhaps just starting. You should be familiar with the code of conduct for the primary professional society, ACM. You can read the ACM Code of Conduct HERE.
We work to maintain an environment supportive of learning in the classroom and laboratory. Towards that end, we require that you be courteous to and respectful of your fellow participants (i.e., classmates, instructors, GTAs and any tutors). In particular: