Published on Fri Mar 06 2020

Demographic Bias in Presentation Attack Detection of Iris Recognition Systems

Meiling Fang, Naser Damer, Florian Kirchbuchner, Arjan Kuijper

The experimental results point out that female users will be significantly less protected by the PAD, in comparison to males.

0
0
0
Abstract

With the widespread use of biometric systems, the demographic bias problem raises more attention. Although many studies addressed bias issues in biometric verification, there are no works that analyze the bias in presentation attack detection (PAD) decisions. Hence, we investigate and analyze the demographic bias in iris PAD algorithms in this paper. To enable a clear discussion, we adapt the notions of differential performance and differential outcome to the PAD problem. We study the bias in iris PAD using three baselines (hand-crafted, transfer-learning, and training from scratch) using the NDCLD-2013 database. The experimental results point out that female users will be significantly less protected by the PAD, in comparison to males.

Sun Oct 25 2020
Computer Vision
Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settings
Presentation attacks are posing major challenges to most of the biometric modalities. Iris recognition has also been shown to be vulnerable to advanced presentation attacks such as 3D contact lenses. We propose a generalized deep learning-based PAD network, MVANet, which utilizes multiple representation layers.
0
0
0
Tue Sep 01 2020
Computer Vision
Iris Liveness Detection Competition (LivDet-Iris) -- The 2020 Edition
LivDet-Iris is an international competition series open to academia and industry. The aim is to assess and report advances in iris Presentation Attack Detection (PAD) This paper presents results from the fourth competition of the series: LivDet-iris 2020.
0
0
0
Wed Sep 26 2018
Computer Vision
Open Source Presentation Attack Detection Baseline for Iris Recognition
This paper proposes the first, known to us, open source presentation attack (PAD) solution to distinguish between authentic iris images and irises with textured contact lenses. The software is written in C++ and Python and uses only open source resources, such as OpenCV.
0
0
0
Sat Mar 31 2018
Computer Vision
Presentation Attack Detection for Iris Recognition: An Assessment of the State of the Art
Iris recognition is increasingly used in large-scale applications. Presentation attack detection for iris recognition is not yet a solved problem.
0
0
0
Tue Mar 16 2021
Computer Vision
Balancing Biases and Preserving Privacy on Balanced Faces in the Wild
There are demographic biases in current models used for facial recognition. We mitigate the imbalanced performances using a novel domain adaptation learning scheme on the facial features extracted using state-of-the-art technology.
2
0
0
Tue Jun 15 2021
Computer Vision
Demographic Fairness in Face Identification: The Watchlist Imbalance Effect
Researchers have found that the gallery composition of a facial recognition database can induce performance differentials to facial identification systems. This negative effect is referred to as the "watchlist imbalance effect" This study represents the first detailed analysis of the watch list imbalance effect.
8
0
0