[1] R. Hartley and A. Zisserman. Multiple View Goemetry in Computer Vision. Cambridge University Press, 2nd edition, 2004.

Probably the best known text on 3D vision. I haven't looked in the second edition but the earlier edition had good descriptions of the epipolar geometry that is used in the course. There is much more in this book than just the basic 2 view geometry.
[2] L. Shapiro and G. Stockman. Computer Vision. Prentice-Hall, 2001.

Looks like this would be a pretty good reference. I haven't read into the book however, and I dont know how well things are covered. It should cover much of the 2D aspect of the course and also a reasonable covereage of the 3D material.
[3] W.E. Snyder and H. Qi. Machine Vision. Cambridge University Press, 2004.

This book is a new book that I haven't had a chance to read yet. It focuses almost exclusively on 2D vision and probabilistic classification. There are good sections on linear filters, morphology, Segmentation, Hough transforms, template matchin and a nice introduction to neural networks. This book aligns quite nicely with the 2D part of the course
[4] B. Jähne. Digital Image Processing. Springer, 5th, revised and extended edition, 2002.

This book is a recent edition of a classic in the field. It has a theoretical flavour for 2D image processing. It provides good theoretical developments of tools such a 2D fourier theory, probability theory, etc, in the context of image processing. It has some useful info about sampling. There is a good section on edge detection and motion identification and some reasonable material on segmentation, morphology and classification. It doesn't fit particularly well with the structure of the course.
[5] D. Forsyth and J. Ponce. Computer Vision; A modern approach. Prentice Hall, 2003.

This book provides a moderate coverage of issues in computer vision with a strong focus on 3-D vision. It has a poor coverege of 2D vision techniques, covering only linear filtering techniques and colour. It has a reasonable development of epipolar geometry and 3D vision, although it is not the best written I have seen. There is a nice section on segmentation and probabilistic classification. It then has a wide range of topics covered in some detail on contemporary research issues. Generally a good book but not very well aligned with the course.
[6] Y. Ma, S. Soatto, J. Kosecka, and S. Sastry. An invitation to 3-D vision; From images to geometric models. Interdisciplinary applied mathematics. Spinger, 2004.

This book is concerned primarily with the geometry of vision. It contains no detail on 2-D image processing or probabilistic classification. It looks well written but pitched at an advanced level. Good long term investment for people looking to do further work in Computer Vision.

This file has been generated by bibtex2html 1.63