Class Description: From Minority Report, Angels & Demons, Mission Impossible, Blade Runner, Gattaca, and The Bourne Identity to The Simpsons and The Incredibles, biometric technologies like face recognition, fingerprint recognition, iris scans, and voice recognition are either a nearly impenetrable barriers to be cleverly foiled or the butt of a joke. Yet, biometrics are used every day to auto-tag photos on Facebook and iPhoto as well as in hardcore applications in immigration control and counter terrorism.
Biometrics are used to identify individuals from measurements of the face, hand geometry, iris, retina, finger, ear, voice, speech, signature, lip motion, skin reflectance, DNA, and even body odor. The first half of the course provides the background in machine learning and imaging for anyone who has taken calculus, linear algebra and probability and statistics. The second half of course will detail individual biometrics, methods for spoofing biometrics, and policy implications.
In a project spaced over the quarter, students will implement a biometric method, system, or application of their choice and appropriate to their background. Past topics have included face recognition using Xbox Kinect, identification from electrocardiograms, face recognition for Chez Bob, gesture interfaces, and recognition from wet fingerprints.
Texts: See E-reserve at: http://reserves.ucsd.edu/eres/coursepage.aspx?cid=21984&page=docs
Prerequisites: Linear algebra and multivariable calculus (e.g., Math 20A & 20F), probability and statics (e.g., CSE103, Math 183), a good working knowledge of C, C++ or Matlab programming. The course is open to undergraduate and graduate students.
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:
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.
Project Description: Available here
Assignments:
Homework 0: Getting Started with Matlab, Due Thursday, April 10, 2014. Follow the assignment from an older CSE152 class as described in the following PDF file with Assignment 0. A test image for the assignment is here. You only need to hand in hardcopy for Part 2, and the email should be sent to kriegman
Homework 1: Bayes Decision Theory with Multivariate Normal Distributions, Due 4/29/2014
Homework 2: Due 5/6/2014
Homework 3: Due 5/22/2014
Download HandImgs.zip here
Homework 4: Due 6/12/2014
Download fingerprint-images-HW.zip here
| Week | Date/Link To lecture notes | Topic/Readings |
| 1 | Apr. 1 |
Biometric Recognition, A.K. Jain, Nature, September 2007 Linear algebra review Random variables review |
| Apr. 3 | Statistical Pattern Recognition, Bayesian Decision Theory Duda & Hart, Chapter 1, 2.1-2.4 |
|
| 2 | Apr. 8 | Bayesian Decision Theory, Gaussian distributions Duda & Hart, Sec. 2.5-2.8 |
| Apr. 10 | Normal distributions | |
| 3 | Apr. 15 | Image Formation |
| Apr. 17 | Parameter Estimation, Duda & Hart, Sec. 3.1-3.5, 3.7 |
|
| 4 | Apr. 22 | Non-parametric classification Duda & Hart, Sec. 4.1-4.5 |
| Apr. 24 | No class | |
| 5 | Apr. 29 | Nearest Neighbor density estimation and classification |
| May 1 | Linear Discriminant Functions | |
| 6 | May 6 More notes |
Support Vector Machines 1. Duda, Hart & Stork, Sec. 5.11 2. "A Tutorial on Support Vector Machines for Pattern Recognition," Christopher J.C. Burges |
| May 7 | Face Recognition I | |
| May 8 | Face Recognition II | |
| 7 | May 13 | Face Recognition III -- Dimensionality reduction |
| May 15 | No Class R. Zunkel: Hand Geometry based Verification, BIOMETRICS: Personal Identification in Networked Society, Springer, 1998 |
|
| 8 | May 20 | Face Recognition - illumination, pose and attributes |
| May 22 | Guest Lecture - David King | |
| 9 | May 27 | Fingerprint Recognition I Minutiae extraction |
| May 29 | Fingerprint Recognition II: Minutae Matching See Section 6.1.4 of Computer Vision: Algorithms and Applications, Rick Szeliski, Draft |
|
| 10 | June 3 | 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 |
| June 5 | Project presentations | |
| June 10 | Project presentations (during final exam period) 3:00-6:00PM |
