CSE527: Introduction to Computer Vision


Instructor: Prof. Dimitris Samaras

Fall 2014: Tue-Thu 4-5:20 in 2311 Computer Science

Course Syllabus

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. Topics this course will cover include:



1.  Image Formation
     Basic facts about light
     Anatomy of a camera
2.  Image Noise
     Modeling image noise
     Smoothing images
3.  Image Features
     Edge Features
     Point Features
     The Hough Transform
4.  Model Fitting _
     Lines, Curves
     Deformable Models

     Robustness, Maximum Likelihood

5.  Texture

     Scale, Orientation, Fourier Transforms

6.  Illumination

     Shading, Shadows, Interreflections,

     Reflectance properties of materials

7.  Camera Geometry
     Homogenous coordinates, Mosaics
     Euclidean, Affine and Projective Transforms
     Perspective, Orthographic, Weak Perspective
     The consequences of various camera models

     Camera Calibration

8.     Multiple View Geometry - Stereo
The epipolar constraint
The fundamental matrix
Computing correspondences
Recovering depth from stereo

9.   3D Shape from X
Shape from Shading,Photometric   Stereo
Shape from Texture
Range Data

10. Motion
      Motion detection & Optical flow,
      Structure from Motion,

      Image-Based Rendering

11. Segmentation & Grouping

      Grouping, Probabilistic Fitting,

      Nearest Neighbors, EM,

      MRFs and Optimization

      Tracking, Kalman Filtering

12. Object Recognition
      Object representation, Faces
      Probabilistic Classifiers,
      Appearance-based methods,

      Deep Learning Classifiers

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, preferably in C/C++._


There will be homeworks, a final project, and two midterms. Homeworks will be 35%, the project 30%, and the exams 35%. Weights are approximate and subject to change. You are expected to do homeworks (4 or 5) 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.

Midterm 1 date:  Oct 14th 2014

Midterm 2 date:  Dec 4th, 2014

You can have one sheet of paper with notes in the midterms.



Computer Vision: A Modern Approach, Forsyth and Ponce, 2nd ed. Prentice Hall 2011.


(Optional)  Computer Vision: Algorithms and Applications by Richard Szeliski, Microsoft Research: draft at http://szeliski.org/Book/


(Optional)  Computer Vision: Models, Learning, and Inference by S. Prince,  Cambridge University Press, 2012


(Optional)  Introductory Techniques for 3-D Computer Vision by E. Trucco and A. Verri,
Prentice Hall, Upper Saddle River, N.J., 1998


Class notes and a collection of additional readings from journals and conference proceedings will be available through 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 occured, an F grade will be awarded. Discussion of assignments 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. If you don't do the lab yourself, you are likely to fail the exams. 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.


Contact info:

    D. Samaras, Tel. 631-632-8464
    email: samaras@cs.stonybrook.edu
    Office Hours: Tue., 2 pm to 3.30pm Wed 2:30pm to 4pm, or by appointment
                         Computer Science room 2429

    TA :.