Share Course Ware
Natural Sciences > Brain & Cognitive Sciences > Pattern Recognition for Machine Vision
 Pattern Recognition for Machine Vision  posted by  duggu   on 12/25/2007  Add Courseware to favorites Add To Favorites  
Abstract/Syllabus
Courseware/Lectures
Test/Tutorials
Further Reading
Webliography
Downloads
More Options
 
Abstract/Syllabus:

Heisele, Bernd, and Yuri Ivanov, 9.913 Pattern Recognition for Machine Vision, Fall 2004. (Massachusetts Institute of Technology: MIT OpenCourseWare), http://ocw.mit.edu (Accessed 08 Jul, 2010). License: Creative Commons BY-NC-SA

Series of images illustrating color and position clustering.

Example of color and position clustering: Each pixel is represented by a its color/position features (R, G, B, wx, wy), where w is a constant. Clustering is applied to group pixels with similar color and position. (Image by Dr. Bernd Heisele.)

Course Highlights

This course features animations and downloadable lecture notes.

Course Description

The applications of pattern recognition techniques to problems of machine vision is the main focus for this course. Topics covered include, an overview of problems of machine vision and pattern classification, image formation and processing, feature extraction from images, biological object recognition, bayesian decision theory, and clustering.

Technical Requirements

RealOne™ Player software is required to run the .rm files found on this course site.

Syllabus

 
 

Overview

The course is directed towards advanced undergraduate and beginning graduate students. It will focus on applications of pattern recognition techniques to problems of machine vision.

The topics covered in the course will include:

  • Overview of problems of machine vision and pattern classification
  • Image formation and processing
  • Feature extraction from images
  • Biological object recognition
  • Bayesian Decision Theory
  • Clustering
  • Classification

Applications:

  • Object detection and recognition
  • Morphable models
  • Tracking
  • Gesture recognition

The course will have a strong hands-on component. Some additional reading from current research will be provided.

Prerequisites

Basic Linear Algebra, Probability, and Calculus.

Texts

Required Textbooks

Duda, Richard O., Peter E. Hart, and David G. Stork. Pattern classification. 2nd ed. New York, NY: Wiley, 2001. ISBN: 0471056693.

Optional Reading

Mallot, Hanspeter A. Computational Vision: Information Processing in Perception and Visual Behavior. Translated by John S. Allen. Cambridge, MA: MIT Press, 2000. ISBN: 0262133814.

Suggested Further Reading

Forsyth, David A., and Jean Ponce. Computer Vision: a Modern Approach. Upper Saddle River, NJ: Prentice Hall, 2003. ISBN: 0130851981.

Hastie, Trevor, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning: Data Mining, Inference, and Prediction: with 200 full-color illustrations. New York, NY: Springer, c2001. ISBN: 0387952845.

Grading

ACTIVITIES PERCENTAGES
Homework 60%
Final Project 30%
Paper Presentation 10%

Calendar

 
 
lec # TOPICS KEY DATES
1 Overview, Introduction  
2 Vision - Image Formation and Processing Assignment 1 out
3 Vision - Feature Extraction I Assignment 2 out

Assignment 1 due
4 PR/Vis - Feature Extraction II/Bayesian Decisions Assignment 3 out

Assignment 2 due
5 PR - Density Estimation Assignment 3 due
6 PR - Classification Assignment 5 out
7 Biological Object Recognition Assignment 6 out

Assignment 5 due
8 PR - Clustering Assignment 7 out

Assignment 6 due 1 week after it is posted
9 Paper Discussion  
10 App I - Object Detection/Recognition Assignment 7 due
11 App II - Morphable Models  
12 App III - Tracking  
13 App IV - Gesture and Action Recognition  
14 Project Presentation  
 

 




www.sharecourseware.org   Tell A Friend