Image of vision

UB Computer Science and Engineering

CSE 473/573: Computer Vision and Image Processing (CVIP)

Fall 2014
[ Home | Schedule | Course Materials | Final Project | Piazza ]

 

Example of automated scene interpretation

Nwogu, Zhou, Brown - AAAI 2011

 

Instructor: Ifeoma Nwogu (Office hours: M 4:00PM - 4:50PM; W 2:00PM - 2:50PM); 113M Davis Hall
TA: Devansh Arpit (Office hours:T 2:00PM - 2:50PM); 113V Davis Hall
Radha Dasari (Office hours: M 11:00AM - 11:50AM); 301A - Multimedia Lab, Davis Hall
Lecture: MWF 3:00PM - 3:50PM (Hochstetter Hall 114) 
Recitations:W 4:00PM - 4:50PM Davis 113Y
R  3:00PM - 3:50PM Davis 113Y
Prerequisites: Basic knowledge of probability, linear algebra, and vector calculus. MATLAB programming experience and previous exposure to image processing will be helpful, but not required.

 

Announcements

Nov 24, 2014: Midterm date moved to Monday December 1, 2014

Becasue of the class cancelations and the closure of the uNiversity last week due to unforseen weather problems, the midterm has now been postponed to Monday, Dec 1, after the Thanksgiving break. The contents and format for the exam will remain the same as discussed in class, as this is just a date change.  Please take note. 

Oct 29, 2014: Some changes have been made to the overall class schedule

We have incorporated more lectures on probabilistic graphical models as related to computer vision in to the class schedule. This is to accomodate many of the students who have not taken courses in machine learning yet. We will tackle much of these from 1st principles over a two-week period and attempt to focus only on what is needed in vision applications. More rigourous learning paradigms will be reserved for the actual machine learning courses.

Oct 27, 2014: Homework 3 DUE DATE moved to Saturday Nov 15th, 2014 at 5 pm

Homework 3 is now due on Saturday Nov 15th at 5pm.

Oct 2, 2014: Class has been cancelled for Friday Oct 3rd, 2014

There will be a computational and data-enabled science and engineering seminar held at 113A Davis hall from 3-4pm on that Friday. Dr. Keith Dalbey from Sandia National Labs will be speaking on adaptive sampling methods. For students taking machine learning, you might find this interesting. Homework is still due on Friday Oct 3rd at 5pm.

Sep 29, 2014: Quiz 1 and 2 scores have been released on piazza

Please pick up your quiz scripts from recition in 113Y or from Radha's lab 31? Davis Hall (during his office hours) and double-check with the results posted on piazza to make sure there are no discrepancies.

Sep 15, 2014: Files for homework 1 have been released on piazza

The first programming assignment has been released under the resource tab on piazza. Please download the questions and data files and do START EARLY! The homework is due on Friday Oct 3rd at 5pm.

Sep 9, 2014: Going forward all recitations will be held at 113Y Davis Hall at the previously scheduled times

Again,pls bring your laptops with access to Matlab either on the CSE machines or locally. Note that the times have not changed, just the location.

Sep 3, 2014: Recitations today and tomorrow 9/4 will be held at 113Y Davis Hall at the previously scheduled times

This week, recitations will cover introductory MATLAB functions. Pls bring your own laptops with access to Matlab either on the CSE machines or locally. It will be a hands-on class led this week by Devansh.

Aug 25, 2014: Welcome to CSE 473/573!

Make sure to check out the course info below, as well as the schedule for what's up ahead.

Good luck with your semester!

CSE 473/573 staff

Overview

This course provides an introduction to computer vision and image processing by emphasizing the middle ground between image processing and artificial intelligence, using pattern recogniton tools. Topics include image formation and representation, feature detection, motion estimation and tracking, object detection and recognition, and case studies of current computer vision research.  We will briefly cover deep networks and discuss how these are playing a stronger role in vision. Students will receive a broad presentation of the field and will be expected to implement several computer vision algorithms throughout the semester.

Assignments and Quizzes

The assignments in this class are comprised of mini programming projects in MATLAB. We anticipate a total of four programming assignments throughout the semester. These assignments are designed to give you both theoretical and practical experience with the material discussed in class. See the schedule for more details. Assignments will be posted on Piazza and are due by 5 p.m. on the specified day. 

You should submit a soft copy of your work by uploading your code (and all files needed to run it, images, etc) using CSE_SUBMIT. Solutions will be discussed in recitations after the assignment due dates.

Quizzes will be given on (an almost) weekly basis in class and we expect a total of about 10 quizzes over the course of the semester. Solutions to the quizzes will  be discussed in class. Students can pick up thier quiz papers from Radha Desari any week day between 5:00 and 6:00pm at 301A Davis Hall. Collaborations are NOT allowed for quizzes. 

Late Policy. Ample time will  be given for the programming assignments, so by 5p.m. of the due date, CSE-SUBMIT will stop accepting submissions. Students who miss a quiz will be able to make up with other quizzes in the course of the semester. Based on the number taken, students might be able to drop quizzes with low scores or where they were "no-shows".

Collaboration Policy. We allow discussing the programming assignments with one or two classmates,  but coding and writing of reports must be done individually unless specifically instructed otherwise. You are also encouraged to search the Web for tips or code snippets, provided this does not trivialize the assignment and rob you of your learning opportunity. You must list your collaborators as well as the extent of collaboration in your project report. You must also explicitly acknowledge all external sources in your project report. Plagerism detection software will be used for assessing originality of assignments.

Academic integrity: Students caught cheating (copying from other students or unacknowledged sources on the Web), will receive a zero grade for that assignment or test. Repeat offenses will result in an automatic F grade and dismissal from the course.

Course Exam

The exam will cover a comprehensive set of questions from the topics covered throughout the semester.

GradingCp2

Grading will be comprised of:

Class participation (especially on Piazza) will also be taken into account.

Text

A set of class notes will be available on this website before each lecture. Additional recommended books and resources are listed in the course materials page.