Courses

TECH 58100 — Biometrics

This course will cover the fundamental concepts and design implications required to implement biometric systems. Key approaches and machine learning techniques specific to vision based, speech based, and behavioral based biometric systems will be discussed. Biometric system performance evaluation and issues related to security and privacy will also be addressed. Topics include: the basic biometric approach, features and feature extraction, data set formats, supervised and unsupervised machine learning, dimensionality reduction and performance evaluation, image based biometric techniques, speech based biometric techniques, behavioral based biometric techniques, and biometric problems and ethical issues.

Prerequisites: Programming skills up to data structures and knowledge of statistics will be useful. No prior experience with biometrics or machine learning is required.

Time & Place

6:30pm-9:30pm
Wednesday
129 Powers

Textbook

Biometrics: Personal Identification in Networked Society
Jain, Bolle, Pankanti

Data Mining: Practical Machine Learning Tools and Techniques
Witten, Frank

Instructor

Ricardo A. Calix, Ph.D.
Computer Information Technology and Graphics
Purdue University Calumet
ricardo.calix@purduecal.edu

Office Hours

Tuesday and Thursday (2-4 PM)
279 Gyte

Reading Materials

reading list
 

Assignments

Assignments: There will be 4 individual assignments with informal lab demonstrations plus one final project with a formal in-class presentation. Graduate students will have one additional writing assignment associated with the final project.

The grading of each assignment:

Implementation

To be determined.

Documentation

To be determined.

Demonstration

The live, in-lab demonstration and description of your completed project. Be ready for this.

Lagniappe

Something extra. You are free to enhance your submission in any way you like. Your addition should be creative.

 

Useful Code

Example problems will be provided as required. 

We will use the following software:

  1. MatLab
  2. Python
  3. Praat
  4. Weka
  5. Octave
  6. Accord.Net

The following libraries may be of use.

  1. NLTK
  2. LibSVM
  3. Image processing Toolbox for MatLab

 

Calendar Spring 2012

Sun Mon Tue Wed Thu Fri Sat
Jan 15 Jan 16 Jan 17
L1: The Biometric System Pipeline
Jan 18


 
Jan 19
Lab 1: Blood Vessel Recog. in Matlab
Jan 20 Jan 21
Jan 22 Jan 23 Jan 24

L2: Foundations and Hand Geometry

Jan 25
 

 
Jan 26

Lab 2: Machine Learning with Weka 1

Jan 27 Jan 28
Jan 29 Jan 30
 
Jan 31

L3: Machine Learning 1

Feb 1
 

 

Feb 2
Lab 3: Machine Learning with Weka 2

Feb 3 Feb 4
Feb 5 Feb 6 Feb 7
L4: Machine Learning 2
Feb 8
 

 
Feb 9
Lab 4: Image Analysis Basics with Matlab
Feb 10 Feb 11
Feb 12 Feb 13 Feb 14
L5: Machine Learning 3
 
Feb 15
 
 
Feb 16
Lab 5: WEKA Experimenter and PCA
Quiz 1
Feb 17 Feb 18
Feb 19 Feb 20 Feb 21
L6: Image Segmentation
Feb 22
 
 
Feb 23
Lab 6: Image Segmentation with Matlab
Feb 24 Feb 25
Feb 26 Feb 27 Feb28
L7: Face Recognition and EigenFaces

Feb 29
 

 

Mar 1
Lab 7: PCA and EigenFaces
Mar 2 Mar 3
Mar 4 Mar 5 Mar 6
 

Mid-Term Exam

Mar 7

 

Mar 8
Lab: Retina and other Biometrics
Mar 9
 
Mar 10
Mar 11 Mar 12 Mar 13
 
Mar 14 Mar 15
 
Mar 16 Mar 17
Mar 18 Mar 19 Mar 20

L8: Finger Print Recognition

 

Mar 21
 
Mar 22

Lab: Finger Print & Project Prototype Demo

Mar 23 Mar 24
Mar 25 Mar 26 Mar 27

L9: Speech Recognition

 

Mar 28

Mar 29
Lab 8: Speech Processing with Praat
Mar 30 Mar 31
Apr 1 Apr 2 Apr 3
L10: Speech Recognition and Text processing
Apr 4
 

 

Apr 5
Lab 9: Sinsum2 and NTLK
Apr 6 Apr 7
Apr 8 Apr 9 Apr 10
L11: Keystroke Recognition and other Behavioral Biometrics
Apr 11 Apr 12
 

Quiz 2

Apr 13 Apr 14
Apr 15 Apr 16 Apr 17
L12: Hidden Markov Models, Naive Bayes, and other Probabilistic Approaches
Apr 18
 

 

Apr 19
Lab 10: NLTK and HMMs with Python for behavioral biometric analysis
Apr 20
 
Apr 21
Apr 22 Apr 23 Apr 24

L13: Systems Behavior and MINDS

 

Apr 25
 
Apr 26

Lab: Case Python-NIDS & Extract Feature

 

Apr 27
 
Apr 28
Apr 29 Apr 30

Concentrated Study

May 1
Term Project Presentations
May 2

Concentrated Study

May 3
Course Wrap-up
May 4
 
May 5
May 6 May 7
Finals
May 8
Finals
May 9
Finals
May 10
Finals
May 11
Finals
May 12