CSci 4968 and 6270: Computational Vision, Fall 2011

Homework and Programming

Homework will involve solving mathematical problems, developing algorithms, and writing programs. The mixture of these will vary between assignments, although the programming aspect will tend to be the most important.

Programming can be done in Matlab with the Image Processing Toolkit or in C or C++, using OpenCV or VXL. If you use one of the latter, you will need to include some way of examining images and other results. My strong suggestion for this course is use of Matlab. If you continue with computer vision beyond this course, especially for working in industry, you should eventually transition to writing in C, C++ or Java.

Programming can be done in Matlab or in C or C++. My strong recommendation is Matlab, at least for this course. If you choose to use C or C++, you will want to make use of either OpenCV or VXL. The former is widely used. The latter is used in my lab, mostly for historical reasons, and it powerful and flexible, if a bit daunting.

Most students are likely to want to use Matlab, together with the Image Processing Toolkit. Students who don't already have these on their computer may sign up and download through RPI's campus system. Below you will find a selection of on-line resources for learning Matlab. Often, however, the simplest thing to do is type a query into a search engine (for example, for homework 1, try to learn about nlfilter).

• Matlab Summary and Tutorial
• The MathWorks - MATLAB Tutorial
• Matlab Primer
• On-line Matlab Help
• Writing Fast Matlab Code (pdf)
• Code Vectorization Guide
• Matlab Programming Style Guidelines (pdf)

Books

Many books on computer vision have been published over the years. We will be using the on-line textbook, Computer Vision: Algorithms and Applications , which Dr. Richard Szeliski of Microsoft Research has just finished writing. See his website for links to other computer vision courses taught throughout the country.

Here are several other books that students might find useful:

• Computer Vision a Modern Approach, Forsyth and Ponce, Prentice Hall, 2003. One of the most commonly-used books over the past decade, written by senior researchers in the field.
• Multiple View Geometry in Computer Vision, Hartley and Zisserman, Cambridge University Press, 2004. An excellent text on projective geometry, cameras, and estimation of 3d geometry.
• Introductory Techniques for 3-D Computer Vision, Trucco and Verri, Prentice Hall, 1998. An algorithmic approach.
• Pattern Classification, Duda, Hart and Stork, Wiley Interscience, 2001. Statistical techniques for two-dimensional pattern recognition. An excellent reference.
• Pattern Recognition and Machine Learning, Bishop, Springer, 2006. An important book on the use of machine learning in image analysis.
• An Introduction to Linear Algebra, Strang, Wellesley-Cambridge Press, 4th edition, 2009. My favorite book on linear algebra.

On-line Resources

• The Computer Vision Homepage (links to vision sites around the country).
• CVonline (a compendium of Computer Vision Bibliographic Information).

Handouts

• Course syllabus
• Introduction pptx, pdf
• Lectures 2 and 3 on images and image processing
• Homework 1
• Lectures 4 and 5 on edges and lines.
• Lectures 6, 7 and 8 on segmentation, including K-means, mean-shift and graph-cuts.
• Homework 2 and the dogs.jpg
• Lectures 9, 10 and 11 on transformations and camera models.
• Homework 3
• Lectures 12 and 13 on SIFT
• Lecture 14 on calibration
• Lecture 15 on homography estimation and mosaics
• Homework 4 and associated image pairs hw4-pairs.zip
• Lecture 17: an overview of object recognition and an introduction to classifiers, principal component analysis and eigenfaces.