Image Quality Assessment for Fake Biometric Detection: Application to Iris, Fingerprint, and Face Recognition

By Javier Galbally, Sébastien Marcel, Julian Fierrez. IEEE Transactions on Image Processing, 2014

605 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/30a71472be794244b3b3cc14d963e7db4521cc7a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Presentation Attack Detection for Face Recognition Using Light Field Camera (2015, methodology): “The proposed method I (c) indicates the performance improvement of over 4% when compared with the second best method based on image quality analysis [4].”
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, methodology): “For the second case, they evaluated detection approaches based on: i) raw faces as features, and ii) image quality measures (IQM) [102].”
Presentation Attack Detection Methods for Face Recognition Systems (2017, background): “The third type of static approach includes hybrid schemes that combine more than one attribute [Galbally et al. 2014b; Wen et al. 2015], the use of client identity information [Chingovska and Anjos 2015], the characterization of the defocus property of the captured face image [Kim et al. 2015b;…”
Secure Face Unlock: Spoof Detection on Smartphones (2016, methodology): “Spoofing detection methods based on image quality analysis utilize the image quality differences between live face images and spoof face images [19], [20], [44].”
Face Spoof Detection With Image Distortion Analysis (2015, background): “Compared to [22], our work is different in the following aspects: (1) While 25 features are required in [22] to get good results, no face-specific information has been considered in designing informative features for face spoof detection .”
Single-Side Domain Generalization for Face Anti-Spoofing (2020, methodology): “The texturebased methods utilize hand-craft descriptors or data-driven deep learning to extract texture cues discriminative between the real faces and the fake ones, such as the color [5], distortion cues [11, 39], etc.”
Biometrics Systems Under Spoofing Attack: An evaluation methodology and lessons learned (2015, background): “Accordingly spoofed face images tend to exhibit degraded facial texture due to reproduction or printing on the spoofing medium (a photograph) and the two imaging systems [10].”
Biometric Antispoofing Methods: A Survey in Face Recognition (2014, background): “Therefore, it is important to find complementary countermeasures and study the best fusion approaches in order to develop liveness-detection techniques that succeed at achieving a high performance over different spoofing data [165], [185].”
Deep Anomaly Detection for Generalized Face Anti-Spoofing (2019, methodology): “They obtain a 139-length feature vector from the concatenation of the quality measurements proposed in [14] and [33].”
Deep Representations for Iris, Face, and Fingerprint Spoofing Detection (2014, background): “Recently, Galbally et al. [76] proposed a general approach based on 25 image quality features to detect spooﬁng attempts in face, iris, and ﬁngerprint biometric systems.”
Robust Scheme for Iris Presentation Attack Detection Using Multiscale Binarized Statistical Image Features (2015, methodology): “The use of software based approaches exhibit additional advantages when compared to hardware based approaches such as [4]: non-invasive, fast, robust, user friendly and low cost.”