Biometrics and Machine Learning Group
Latest news
We are pleased to announce that Mateusz Trokielewicz defended (with honors) his doctoral dissertation entitled „Iris Recognition Methods Resistant to Biological Changes in the Eye” , supervised by prof. Czajka and prof. Pacut, on the 18th of July, 2019.
Iris scanner can distinguish dead eyeballs from living ones: MIT Technology Review reports on our recent developements in the field of presentation attack detection for cadaver irises.
We are pleased to announce that Mateusz Trokielewicz received the EAB European Biometrics Research Award 2016 for research on iris recognition reliability including template aging, influence of eye diseases and post-mortem recognition.
Is That Eyeball Dead or Alive? Adam Czajka discusses the prevention of iris sensors accepting the use of a high-resolution photo of an iris or, in a grislier scenario, an actual eyeball. For full article, please see IEEE Spectrum.
Assignments
Biometrics (CSE 40537/60537) ->Assignments
Important note on biometric data usage
In each assignment you will use your own biometric samples, collected during practical classes. Your biometric data will be stored by the instructor in the encrypted container, and will be used only for the purpose of this Biometrics course. The data will be permanently deleted after concluding the course.
Using your own biometric data during assignments has many advantages, e.g. you can interact with real biometric systems. However, should you have any doubts related to the data collection or processing, please contact the instructor to work out the alternative solution (e.g. finding appropriate samples in one of the public biometric datasets). Your decision on not using your own biometric data during assignments is fully permissible and it will not influence the grading of your work.
Software and data distribution
Due to security reasons, the biometric data and the software will be distributed only during the practical classes, and will not be posted to the webpage.
How to complete the assignments
- You will need MATLAB software installed on a Windows machine to complete the assignment. You may use University computers, or download MATLAB from https://oit.nd.edu/software-downloads/ (your netID and the password is required).
- Read the instructions and solve all tasks using the software and biometric data distributed during the class.
- There is no formal template for providing the answers. Use a tool that you like. I accept:
- a single Word or PDF document incorporating all text answers and the resulting images,
- an email with the text answers and the resulting images attached as a single zip file,
- a mixture of the above.
- Send your answers to aczajka@nd.edu by the deadline indicated in each assignment.
- Should you have any problems with sending the results, you can bring them personally on the USB flash drive during my office hours (Fitzpatrick 355C, 10:00-11:00 AM, MWF), or just before/after the classes.
Instructions
Assignment 5: Presentation attack detection (PAD) in iris biometrics (PDF)
Interim report: by the end of Sunday, December 7, 2014
Full report: by the end of Sunday, December 14, 2014
Assignment 4: Presentation attack detection (PAD) in fingerprint biometrics (PDF)
Interim report: by the end of Sunday, November 23, 2014
Full report: by the end of Monday, December 1, 2014
Assignment 3: Build your own handwritten signatures recognition method (PDF)
Interim report: by the end of Sunday, November 2, 2014
Full report: by the end of Wednesday, November 5, 2014
Assignment 2: Build your own iris recognition method (PDF)
New deadline: send your answers by the end of the day Tuesday, October 14, 2014
Assignment 1: Fingerprint recognition (PDF)
New deadline: Monday 9/29/2014, 11:00 AM