CS6720 --- Pattern Recognition

(Summer I 2010 - Call No. 21636)

(Web site: http://www.cs.wmich.edu/~yang/teach/cs6720)

Instructor: Li Yang (yang@cs.wmich.edu)
Lecture Time: TR 5:30-8pm
Classroom: C124
Office: B248
Office Hour: TR 8-9pm, and by appointment.


What is Pattern Recognition?

Pattern recognition focuses on the problem of how to automatically classify physical objects or abstract multidimensional patterns (n points in d dimensions) into known or possibly unknown categories. Traditional example applications include character recognition, handwriting recognition, document classification, fingerprint classification, speech and speaker recognition, white blood cell (leukocyte) classification, military target recognition, and object recognition by machine vision systems in assembly lines among others. The design of a pattern recognition system usually requires the following modules: (i) sensing, (ii) feature selection and extraction, (iii) classification, and (iv) evaluation. In recent years, the availability of low-cost high-resolution sensors (e.g., CCD cameras, microphones, and scanners) and data sharing over the Internet have resulted in huge repositories of digitized data. Need for efficient archiving and retreival of the data has fostered the development of pattern recognition algorithms in new application domains (e.g., text, image and video retrieval, bioinformatics, and face recognition).

There are three main approaches for pattern recognition: (1) statistical methods, (2) template matching, and (3) syntactic methods. This course will introduce the fundamentals of statistical methods and template matching in class lecture and leave syntactic methods to be introduced by student presentations.


Announcements:

Important announcements will come here.


Graduate Catalog Data:

Name: CS6720 - Pattern Recognition
Credit Hours: 3
Prerequisites: CS4310 and STAT3640

Course Description:

This course introduces fundamental statistical methods for pattern recognition and covers basic algorithms and techniques for analyzing multidimensional data, including algorithms for classification, feature selection, and dimensionality reduction of the data. The course will also introduce students to active research topics. Students are expected to do independent reading of research papers and make class presentations.

Objectives:

Learning Outcomes:

Upon completion of this course, students should be able to:

Textbooks:

Topics and Schedule:

  1. Introduction and background
  2. Bayes classification.
  3. Linear classifier
  4. Nonlinear classifier
  5. Midterm exam
  6. Feature selection
  7. Dimensionality reduction and feature generation
  8. Template matching
  9. Markov chain and hidden Markov model
  10. System evaluation
  11. Technical presentation
  12. Final exam

Evaluation:

Academic Integrity

The following code is required to be included in this syllabus:

You are responsible for making yourself aware of and understanding the policies and procedures in the Undergraduate (pp. 271-272) [Graduate (pp. 24-26)] Catalog that pertain to Academic Integrity. These policies include cheating, fabrication, falsification and forgery, multiple submission, plagiarism, complicity and computer misuse. If there is reason to believe you have been involved in academic dishonesty, you will be referred to the Office of Student Judicial Affairs. You will be given the opportunity to review the charge(s). If you believe you are not responsible, you will have the opportunity for a hearing. You should consult with me if you are uncertain about an issue of academic honesty prior to the submission of an assignment or test.