CSCI 363
    Computational Vision

    College of the Holy Cross, Spring 2023

    Home | | Schedule | | Assignments | | Lecture Notes

    Instructor
    Constance Royden
    Office: Fenwick 204, Haberlin 308
    Extension: 2472
    Email: croyden@holycross.edu
    Office Hours:

    • Mon 1:00 - 2:00 p.m.
    • Wed 11:00 - noon
    • or by appointment.

    Lecture times
    Tues, Thurs 12:30 - 1:45 p.m.

    Course description
    Computational vision is an important field within computer science that combines information from mathematics, computer science and neuroscience to understand how a machine or biological visual system works. The study of computer vision has been an active field and has generated many exciting results that increase our understanding of the complex and remarkable task of interpreting the world around us from visual information. This course will bring together results from the field of computer vision and from the field of biological vision and examine how different approaches can give us the ability to recognize objects or interpret motion from a 2 dimensional image that changes over time.

    The course offers an introduction to the algorithms underlying machine and biological visual systems. It examines the processes involved in converting a 2-dimensional image to a 3-D representation of the physical world. Computational models of visual processing will be compared to physiological and psychophysical results from human and other biological visual systems. The topics covered include: edge detection, stereopsis, motion computation, shape from shading, color and object recognition.

    Prerequisites
    The prerequisite for this class is CSCI 132, Data Structures, and Calculus.
    You should feel comfortable with basic C++ programming, and with basic calculus concepts such as derivatives and integrals.

    In addition you should be prepared to learn some new mathematical techniques. For certain concepts in computational vision, we'll need to use some mathematical methods that may be new to you, such as convolutions and fourier analysis. We will learn these methods in class.

    Textbook and Readings
    Vision Science. Photons to phenomenology.
    by Palmer.
    This textbook covers a broad range of vision science from biological, psychological and computational perspectives.

    The readings in the textbook will be supplemented with readings that will be handed out. You will be expected to read the assigned material before class and be prepared to discuss the concepts from the readings. In addition, you will be asked to hand in written answers to selected questions on the readings.

    Course requirements
    Exams: There will be two midterm exams during the semester. They will be on the following dates:

      Exam 1: Thursday, Feb 23, in class
      Exam 2: Tuesday, April 4, in class

    There will be a final exam during the regular exam period

    Homework Assignments: There will be homework assignments periodically during the semester. These will involve some programming using Matlab or C++ and some paper and pencil problem solving.

    Course Project: Students will work in groups to complete a course project. The project will involve researching an area of vision science and writing a paper on your findings. Projects will be presented to the class at the end of the semester.

    Grading

      Participation: 5%
      Homework: 25%
      Project: 10%
      Midterm exam 1: 20%
      Midterm exam 2: 20%
      Final Exam: 20%

    Late Policy
    Assignments are due at the beginning of class on the assigned due date. Late assignments will be marked down 10% for each day late. That is, assignments turned in after the time they are due will be marked down 10%, assignments turned between 24 and 48 hours after the due date will be marked down 20%, and so on. The penalty will be determined when the assignment is physically transferred to the instructor or signed in by any Math/CS faculty member or the department secretary. Late work will not be accepted after the graded assignment is returned to the class.

    Collaboration Policy
    You are allowed to discuss strategies for solving homework problems with other students, however any work you turn in must be your own work (i.e. you may not simply copy another student's answers and turn them in as your own). In addition you must clearly indicate the names of any students you work with on each assignment.

    You may consult public literature (books, articles, etc) for information, but you must cite each source of ideas you adopt.

    Academic Integrity
    Please familiarize yourself with the Math and CS Department's policy on Academic Integrity as well as the College's Academic Integrity Policy.


    Attendance Policy
    Students are expected to attend class regularly and to fulfill all obligations of the course as outlined on this syllabus and discussed during class. I will take attendance each class period and use it in determining your course participation grade.

    If you are unable to attend class in person because you have COVID symptoms or are not cleared through HCClear, you must contact me at least 1 hour before the start of the class session and I will provide you with a zoom link to that session. Zoom links will not ordinarily be available, so you must contact me to obtain one. In the event that I am unable to attend class in person due to COVID symptoms or other reasons, or if multiple students are unable to attend class in person, I may move the entire class session to remote for a short time. If this is the case, I will email you and provide all students with Zoom links to attend the class remotely. Please pay attention to emails from me, since that is the way I will communicate if classes will be given remotely.

    Students should also read and abide by the College's Class Attendance Policy.

    Mask wearing
    Mask wearing policy will be determined by the current state of COVID infections at the College and in the Worcester community. If the College requires masks to be worn, I expect students to follow that policy. As of the beginning of the semester, there is a mask advisory, so I ask all students to wear masks in class and to office hours for the first week and as long as the advisory lasts. This policy may be relaxed later in the semester depending on the amount of COVID circulating in the campus community.


    Recording of class sessions
    Lectures may be recorded by the instructor and made available to students registered for this class using Zoom. Duplication or redistribution of video capture recordings by any other party without the consent of the course instructor is prohibited.

    Consistent with applicable federal and state law, this course may not be video/audio recorded by students, except as an accommodation with permission from the Office of Accessibility Services.


    Accessibility Statement
    Any student who feels the need for accommodation based on the impact of a disability should contact Office of Accessibility Services to discuss support services available. Once the office receives documentation supporting the request for accommodation, the student would meet privately with Disability Services to discuss reasonable and appropriate accommodations. The office can be reached by calling 508-793-3693 or by visiting Hogan Campus Center, room 215A.

    If you are already registered with Disability Services, please be sure to get your accommodation letters and deliver them to your instructors in a timely fashion. Instructors need 4-5 days advance notice to be able to facilitate the process of receiving testing accommodations.


    Statement on confidentiality and Mandatory Reporting


    Home | | Schedule | | Assignments | | Lecture Notes


    Constance Royden--croyden@holycross.edu
    Computer Science 363--Computational Vision
    Last Modified: January 18, 2023
    Page Expires: January 18, 2024