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.
Biometrics (CSE 40537/60537)
Biometrics (CSE 40537/60537) -> Lecture notes
Please read the following remarks below downloading and using these lecture notes.
These lecture notes were prepared for students of the University of Notre Dame in Fall 2014. If you find these notes helpful in your work, please provide the following reference:
"Adam Czajka, Biometrics (CSE 40537/60537), Lecture Notes, Fall 2014, available online http://zbum.ia.pw.edu.pl/EN/node/41"
Please note that all figures and photographs having no credit explicitly indicated in the slides are my own figures and photographs. Please ask if you want to copy and paste them into your lectures or other materials.
These lecture notes cannot be used in any commercial activity.
Lecture 10: Biometric passports
Presentation slides (zipped PDF): What is the biometric passport? Biometrics in e-passports. Structure and security of e-passports. (updated: Dec. 9, 2014 by A.Czajka)
Lecture 9: Statistical evaluation of biometrics
Presentation slides (PDF): Evaluation in biometrics, modeling of uncertainty. Evaluation of data acquisition, enrollment and authentication processed. Use of statistical estimators in biometrics. Statistical hypothesis testing and its relation to biometric evaluation. Selected good practices. (updated: Dec. 7, 2014 by A.Czajka)
Lecture 8: Security of biometrics
Presentation slides (ZIP): Biometric system: components, enrollment, verification, identification. Volnurability of system components. Presentation attacks and their detection, subversive vs. suspicious actions, types of presentation attacks. Security of biometric sensors, fingerprint liveness detection, iris liveness detection. Security of biometric transmission channels. Security of data carriers, biometric smart cards. (updated: Nov. 23, 2014 by A.Czajka)
Lecture 7: Speaker recognition
Presentation slides (PDF): Short history, speaker recognition variants. Pre-processing of voice signals, filtering, detection, representation. Speaker features, formants, Lucier's experiment. Feature extraction: auto-regressive models, independent component analysis (ICA), mel-scale, homomorphic deconvolution, cepstral features. (updated: Oct. 31, 2014 by A.Czajka)
Lecture 6: Recognition of handwritten signatures
Presentation slides (PDF): Definition of a biometric signature. Signature capture. Signature data processing. Global features. Signature comparison, use of classifiers, use of dynamic time warping (updated: Oct. 19, 2014 by A.Czajka)
Lecture 5: Hand biometrics
Presentation slides (PDF): Hand-related modalities. Palm print. Hand geometry. Hand vein recognition. Finger veins. Hand temperature. (updated: Oct. 7, 2014 by A.Czajka)
Lecture 4: Face recognition
Lecture by Prof. Domingo Mery
Presentation slides - Day 1 (PDF)
Presentation slides - Day 2 (PDF)
MATLAB code
Lecture 3: Iris recognition
Presentation slides (PDF): Iris genesis and its structure. Brief history of iris recognition. Iris image capture and representation. Iris image segmentation. Building the iris code. Iris code matching. (complete version, updated: Sept. 25, 2014 by A.Czajka)
Lecture 2: Fingerprints recognition
Presentation slides (PDF): Historical background. Observation levels, basic elements, level 1 features: core and singular points, level 2 features: minutiae, level 3 features. Fingerprint image capture. Fingerprint image pre-processing. Recognition methods. Minutiae detection. Minutiae matching. (updated: Sept. 11, 2014 by A.Czajka - final and full version)
Lecture 1: What is biometrics?
Presentation slides (PDF): Basics, biometric modalities, expected properties of biometrics, brief history of biometrics, biometric system, system errors and decision making (updated: Sept. 2, 2014 by A.Czajka -- corrected slides #39 and #40)