CSE190A

Topics in CSE:

BIOMETRICS

 

Section Id: 570220,

Tuesday, Thursday, 3:30pm - 4:50pm

HSS 1138

 

http://www.cs.ucsd.edu/classes/fa06/cse190-a/

 

 

 

 

 

News:

10/2/06: Project description posted

10/3/06: Confirmed that E-reserves are available at http://reserves.ucsd.edu/eres/coursepage.aspx?cid=9146&page=docs

10/12/06: Homework 1 posted

10/24/06: Homework 2 and Homework 3 posted

10/31/06: Homework 2 has been updated!

 

 

Instructor: David Kriegman

Office: EBU3b, Room 4120

Phone: (858) 822-2424

Email: kriegman at cs.ucsd.edu

Office Hour: Wednesday 1:30-2:30

 

Class Description: Biometrics is the science of determining a person's identity by measuring his/her physiological characteristics. Fingerprinting, most widely known for its role in forensics, was used to sign and validate contracts in the 7th century during China's Tang Dynasty; today, laptop computers use automatic fingerprint recognition instead of passwords. Technologies are being developed to verify or identify individuals based on measurements of the face, hand geometry, iris, retina, finger, ear, voice, speech, signature, lip motion, skin reflectance, DNA, and even body odor. In this course we will explore the advances in biometrics as well as the machine learning techniques behind them.

 

Required Text: none

See E-reserve at: http://reserves.ucsd.edu/eres/coursepage.aspx?cid=9146&page=docs

 

Prerequisites: Linear algebra and Multivariable calculus (e.g. Math 20A & 20F), probability and statistics (e.g., Math 183 or CSE190, A Practical Introduction to Probability and Statistics), a good working knowledge of C, C++ or Matlab programming.

 

Programming: Assignments will include both written problem sets and programming assignments in Matlab. Students can either purchase the Matlab student edition or use copies available on University machines such as are available in the APE Lab

Grading:

Assignments: 40%

Quiz: 10%

Final Project: 50%

Late Policy: Written homework will be due in class and accepted thereafter with a penalty of 10% per day starting from the due date. Programming assignments will have a hand-in procedure described with the assignment, and also has a 10% per day late penalty. No assignments will be accepted after the graded assignments have been returned or the solutions have been released.

 

 

Assignments:

Homework 0: Getting Started with Matlab, Due Thursday, Sept. 28, 2006). Follow the assignment from CSE152 last spring as described in the following PDF file with Assignment 0.  A test image for the assignment is here. You only need to hand it the hardcopy, not the electronic part. If you have already done the tutorial as part of another class, you do not need to repeat Part I, but you need to do Part 2. If you took CSE152 last year, you can hand in your result for part 2 from last quarter.

 

PROJECT: Here is the project description including due dates.

Homework 1: Pattern Classification, due 10/19/06

Homework 2: More Pattern Classification, due 10/31/06

Homework 3: Hand geometry-based recognition, due 11/7/06. Data files

Homework 4: Finding the Candy Man using fingerprints, due 12/1/06, Data files.

 

Syllabus

 

[ Note that this Syllabus is tentative & subject to change]

Week

Date/Link

To lecture

notes

Topic/Readings

1

lec1

Linear algebra review

Random variables review

Intro to Biometrics

A.K. Jain, A. Ross and S. Prabhakar, "An Introduction to Biometric Recognition", BIOMETRICS: Personal Identification in Networked Society, Springer, 1998

2

Sep. 26

Statistical Pattern Recognition, Bayesian Decision Theory

Duda & Hart, Chapter 1, 2.1-2.4

 

Sep. 28

Bayesian Decision Theory, Gaussian distributions

Duda & Hart, Sec. 2.5-2.8

3

Oct. 3

Image Formation

 

Oct. 5

Parameter Estimation,

Duda & Hart, Sec. 3.1-3.5, 3.7

4

Oct. 10

Parameter Estimation, cont

 

Oct. 12

Non-parametric classification

Duda & Hart, Sec. 4.1-4.5

5

Oct. 17

Nearest Neighbor density estimation and classification

 

Oct. 19

Linear Discriminant Functions

6

Oct. 24

Support Vector Machines

1. Duda, Hart & Stork, Sec. 5.11

2. "A Tutorial on Support Vector Machines for Pattern Recognition," Christopher J.C. Burges

 

Oct. 26

Hand Geometry and Recognition

R. Zunkel: Hand Geometry based Verification, BIOMETRICS: Personal Identification in Networked Society, Springer, 1998

7

Oct. 31

Face Recognition I

 

Nov. 2

Fingerprint Recognition I – Guest lecture by Serge Belongie

8

Nov. 7

Fingerprint Recognition II

Minutiae extraction

 

Nov. 9

Fingerprint Recognition III

RANSAC Notes from Hartley & Zisserman

9

Nov. 14

Face Recognition II

 

Nov. 16

Face Recognition III

10

Nov. 21

Iris Recognition

J. Daugman: Recognizing Persons by Their Iris Patterns, BIOMETRICS: Personal Identification in Networked Society, Springer, 1998.

J. Daugman (1993) "High confidence visual recognition of persons by a test of statistical independence." IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15(11), pp. 1148-1161

 

 

Nov. 28

Biometrics Policy

11

Nov. 30

Project presentations

 

 

Notes and links

 

Programming languages: 

The primary language will be Matlab. . Click here for Serge Belongie’s Matlab resource links.

 

A good book on Computer Vision

Introductory Techniques for 3-D Computer Vision, Trucco and Verri (textbook for CSE152)

 

Some General Biometrics books

1. D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, Handbook of Fingerprint Recognition, Springer Verlag, 2003.

2. K. Jain, R. Bolle, S. Pankanti (Eds.), BIOMETRICS: Personal Identification in Networked Society, Kluwer Academic Publishers, 1999.

3. Ruud M. Bolle et al., Guide to Biometrics, Springer, 2004.

 

 

Some useful links: