CSE527: Introduction to Computer Vision

Fall 2016, Tues Thurs 11.30am-12.50pm, Location: MELVILLE LBR W4550
Instructor: Minh Hoai Nguyen, CS 153, Phone: 631-632-8460
Office hour: Tues Thurs 5-6.30pm
TA: Ali Selman Aydin (selman@cs.stonybrook.edu)


The aims of this course are to provide an understanding of the fundamentals of Computer Vision and to give a glimpse in the state-of-the-art, at a moment when the field is achieving “critical mass” and has started having significant commercial applications.

Tentative Syllabus

Date Topic Readings Assignments
29-Aug-2016 Course introduction
01-Sep-2016 Filters and convolution
06-Sep-2016 Labor day - no class
08-Sep-2016 Edges and features HW1 out
13-Sep-2016 Interest points, Harris corner, SIFT
15-Sep-2016 Bag-of-Words model
20-Sep-2016 Supervised Learning for Image Classification
22-Sep-2016 Neural Networks and Deep Learning HW1 due
27-Sep-2016 Neural Networks and Deep Learning HW2 out
29-Sep-2016 Convolutional Neural Networks
04-Oct-2016 Object detection
06-Oct-2016 Camera and Image formation Project proposal due
11-Oct-2016 Multiple views and 3D reconstruction
13-Oct-2016 Stereo HW2 due. HW3 out.
18-Oct-2016 Midterm exam - no class Midterm during class time
20-Oct-2016 Epipolar Geometry
25-Oct-2016 Epipolar Geometry
27-Oct-2016 Structure from Motion
01-Nov-2016 Structure from Motion
03-Nov-2016 Motion Analysis
04-Nov-2016 HW3 due. HW4 out.
08-Nov-2016 Optical Flow estimation Project mid-report due.
10-Nov-2016 Illumination and Shading - guest lecture by Dimitris Samaras)
15-Nov-2016 Document Analysis - guest lecture by Roy Silkrot
17-Nov-2016 Motion Models
22-Nov-2016 Optical Flow estimation - variational inference
23-Nov-2016 HW4 due
24-Nov-2016 Thanksgiving - no class
29-Nov-2016 Last day of class - review
01-Dec-2016 Poster session - no class Poster 10:00am-2:30pm
06-Dec-2016 NIPS - no class or guest lecture
08-Dec-2016 NIPS - no class or guest lecture Project final report due
14-Dec-2016 Final exam - no class Final Exam 5:30-8:00PM

Tentative list of topics

  1. Camera and image formation

    1. Basic facts about light

    2. Anatomy of a camera

    3. Camera parameters and calibration

  2. Filters and features

    1. Image noise

    2. Linear filters and convolution

    3. Gradients, edges, local invariance, SIFT, HOG

  3. Image category recognition

    1. Bag-of-word model

    2. Spatial Pyramid matching

    3. Convolutional Neural Networks

  4. Object detection

    1. Scale pyramid

    2. Sliding window

    3. Object proposal

  5. Multiple views and 3D reconstruction

    1. Homography and image warping

    2. Eipolar geometry

    3. Correspondence and calibration

  6. Motion and tracking

    1. Optical flow

    2. Tracking

    3. Background subtraction

  7. Action/Activity recognition

    1. Human action recognition

    2. Trajectory prediction

    3. Gesture recognition

  8. Grouping and fitting

    1. Segmentation and clustering

    2. Hough transform

    3. Deformable contours

  9. Physics-based vision

Intended Audience:

This course is intended for graduate students with interests in all areas of Visual Computing, such as Computer Vision, Computer Graphics, Visualization, Biomedical Imaging, Robotics, Virtual Reality, Computational Geometry. Prerequisites include a foundation in Linear Algebra and Calculus, and the ability to program, especially Matlab.


There will be 4 homeworks, 1 midterm, 1 final exam, and a project. For the project, you will need to submit a proposal, mid-report, and final report. You will also need to present a poster at the end of the course.

  • Homeworks 40%

  • Project 30%

  • Mid-term exam: 10%

  • Final exam: 20%

Weights are approximate and subject to change. You are expected to do homeworks by yourselves. Even if you discuss them with your classmates, you should turn in your own code and write-up. Final projects can be done by one or two people. Two people projects will be scaled accordingly.

Recommended textbooks

  • Computer Vision: Algorithms and Applications by Richard Szeliski (2010) available online.

  • Computer Vision: A Modern Approach by David Forsyth and Jean Ponce (2004)

  • Multiple View Geometry by R. Hartley and A. Zisserman (2004) link

Readings from these books and notes for all topics will be posted on blackboard

Academic misconduct policy:

Don't cheat. Cheating on anything will be dealt with as academic misconduct and handled accordingly. I won't spend a lot of time trying to decide if you actually cheated. If I think cheating might have occurred, then evidence will be forwarded to the University's Academic Misconduct Committee and they will decide. If cheating has occurred, an F grade will be awarded. Discussion of assignments and projects is acceptable, but you must do your own work. Near duplicate assignments will be considered cheating unless the assignment was restrictive enough to justify such similarities in independent work. Just think of it that way: Cheating impedes learning and having fun. The labs are meant to give you an opportunity to really understand the class material. Please also note that opportunity makes thieves: It is your responsibility to protect your work and to ensure that it is not turned in by anyone else. No excuses!

Disability note:

If you have a physical, psychological, medical or learning disability that may impact on your ability to carry out assigned course work, I would urge that you contact the staff in the Disabled Student Services office (DSS), Room 133 Humanities, 632-6748/TDD. DSS will review your concerns and determine, with you, what accommodations are necessary and appropriate. All information and documentation of disability is confidential.