B657 Computer Vision

B657/P657 Computer Vision

Instructor: Prof. Chen Yu
Time: Spring 2008, Tu, Th, 2:30-3:45pm
Room: LH 115
Class number: 12347

This course is an introduction to computer vision, machine learning, and related topics. The course is intended as an overview, and we shall touch on a lot of topics; some in greater depth than others. A list of representative topics is given below.

Topics:

Image formation and representation: light, cameras, geometry, colors, pixels, quantization, sampling, resolution
Image processing: smoothing, enhancement, edge detection, filtering, etc.
Feature extraction: lines, curves, regions, templates, snakes, hough transform, principle components, etc.
Biological vision: The eye, neurons, brain architecture.
Object representation: 2D, 3D, adjacency graphs, generalized cylinders, skeletons, component models, subspace representations etc.
Statistical machine learning: Graphical Models, Hidden Markov Models, Support Vector Machines, Boosting, Bayesian classification.
Applications: contour detection, face detection and recognition, motion tracking, object tracking and recognition.

Prerequisites:

Basically I will be assuming math such as linear algebra and calculus. This is not a mathematical course, but a fair amount of mathematics is unavoidable. In terms of computer background, you should be able to program well enough to easily write code to implement matrix operations.

Course Books:

The following textbooks are recommended (not required) sources:

Sonka, M., Hlavac, V., & Boyle, R. (2007) Image Processing, Analysis, and Machine Vision. Brooks/Cole Publishing Company, ISBN 053495393X (2nd edition), ISBN 049508252X (3rd edition).
Bishop, C. M. (2006) "Pattern Recognition and Machine Learning ", Springer.

There are a lot of other books on computer vision that are worth taking a look at, or useful references for some areas. Some well known examples are given below.

Ballard, D.H. & Brown, C.M. (1982) "Computer Vision", Prentice Hall, The classic, a little bit dated, but still quite relevant.
Jain, R. & Schunck, B.G. (1995) "Machine Vision", McGraw-Hill, 1995
Davies, E.R. (2005) "Machine Vision: Theory, Algorithms Practicalities," 3nd ed., Morgan Kaufmann

Grading

Homework: 70%
Final Project: 30%
In general, I intend this to be a project-based course, with a grade based on class participation and success in carrying out vision projects. All assignments are mandatory. There will be penalties for late homework unless you have a cogent excuse. These penalties are designed as an incentive to you because the material is cumulative; the penalties also help keep things fair to all students. If you must be late with an assignment, please let me know immediately.

Disclaimer: All the information here is subject to change. Changes will announced in class.

This web page is at URL = http://www.indiana.edu/~dll/B657.html

Schedule

Week	Date	Slides	Reading
1	01/12 01/14	Introduction to Computer Vision and Machine Learning	PRML 2.5.2
2	01/19 01/21	K-Means Clustering Probability Theory	PRML 9.1 PRML 1.2
3	01/26	Optimization	PRML Appendix B and E
4	02/02	Mixture Models and EM Algorithm	PRML 9.2 and 9.3
5	02/09	PCA and Eigenface	Eigenface paper
6	02/16	Edge Detection Canny edge detection and Hough transform
7	02/23	Texture	Paper 1 Paper 2 Paper 3
8	03/02	Object Recognition I	Paper 1 Paper 2 Paper 3
9	03/09	Object Recognition II	Paper 1 Paper 2 Paper 3 Paper 4 Paper 5
10	03/23	Bayesian Concept Learning Nonlinear Dimension Reduction	Bayesian Learning ISOMAP LLE
11 & 12	04/06 & 04/13	Hidden Markov Models	HMM CHMM AHMM Paper 4 Paper 5

Last modified on Jan 25, 2010