Multispectral Biometrics System Framework: Application to Presentation Attack Detection

@article{Spinoulas2021MultispectralBS,
  title={Multispectral Biometrics System Framework: Application to Presentation Attack Detection},
  author={Leonidas Spinoulas and Mohamed E. Hussein and David Geissb{\"u}hler and Joe Mathai and Oswin G. Almeida and Guillaume Clivaz and S{\'e}bastien Marcel and Wael AbdAlmageed},
  journal={IEEE Sensors Journal},
  year={2021},
  volume={21},
  pages={15022-15041}
}
In this work, we present a general framework for building a biometrics system capable of capturing multispectral data from a series of sensors synchronized with active illumination sources. The framework unifies the system design for different biometric modalities and its realization on face, finger and iris data is described in detail. To the best of our knowledge, the presented design is the first to employ such a diverse set of electromagnetic spectrum bands, ranging from visible to long… 
Multi-Modal Fingerprint Presentation Attack Detection: Evaluation on a New Dataset
TLDR
The results indicate that the power of the approach stems from the nature of the captured data rather than the employed classification framework, which justifies the extra cost for hardware-based (or hybrid) solutions.
On the Use of an Hyperspectral Imaging Vision Based Measurement System and Machine Learning for Iris Pigmentation Grading
TLDR
An interesting application of ML techniques to an Hyperspectral Imaging System, devoted to the analysis of the iris pigmentation, to point out the possible ML techniques that can be employed, the needed dataset and the possible advantages offered by the hyperspectral approach, compared to the conventional visible light imaging.
Beyond the Visible: A Survey on Cross-spectral Face Recognition
TLDR
An overview of CFR is provided, by formalizing the CFR problem and presenting related applications, and techniques that have been proposed to extract and compare heterogeneous features emerging from different spectral bands are described.
Detection and Continual Learning of Novel Face Presentation Attacks
TLDR
This paper enables a deep neural network to detect anomalies in the observed input data points as potential new types of attacks by suppressing the confidence-level of the network outside the training samples’ distribution and uses experience replay to update the model to incorporate knowledge about newtypes of attacks without forgetting the past learned attack types.
Explaining Face Presentation Attack Detection Using Natural Language
TLDR
The first introduction of a joint biometrics-NLP task and the effectiveness of the model for generating proper PAD explanations through text as well as the power of the sentence-wise losses are shown.
On the Effectiveness of Impedance-Based Fingerprint Presentation Attack Detection
TLDR
A fingerprint capture device based on thin film transistor (TFT) technology has been modified to additionally acquire the impedances of the presented fingers to train a presentation attack detection (PAD) algorithm.

References

SHOWING 1-10 OF 61 REFERENCES
Towards Fingerprint Presentation Attack Detection Based on Convolutional Neural Networks and Short Wave Infrared Imaging
TLDR
A new fingerprint presentation attack detection method based on convolutional neural networks and multi-spectral images extracted from the finger in the short wave infrared spectrum is presented.
Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network
TLDR
A multi-channel Convolutional Neural Network-based approach for presentation attack detection (PAD) and the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks is introduced.
Biometric Presentation Attack Detection: Beyond the Visible Spectrum
TLDR
A novel fingerprint presentation attack detection (PAD) scheme based on a new capture device able to acquire images within the short wave infrared (SWIR) spectrum, and an in-depth analysis of several state-of-the-art techniques based on both handcrafted and deep learning features is presented.
Multi-Modal Fingerprint Presentation Attack Detection: Analysing the Surface and the Inside
TLDR
A multi-modal fingerprint PAD which relies on an analysis of the surface of the finger within the short wave infrared (SWIR) spectrum, and the inside of thefinger thanks to the laser speckle contrast imaging (LSCI) technology is proposed.
Design of an Active Multispectral SWIR Camera System for Skin Detection and Face Verification
TLDR
This work proposes an approach to face verification based on spectral signatures of material surfaces in the short wave infrared (SWIR) range that allow distinguishing authentic human skin reliably from other materials, independent of the skin type.
Multi-Modal Fingerprint Presentation Attack Detection: Evaluation on a New Dataset
TLDR
The results indicate that the power of the approach stems from the nature of the captured data rather than the employed classification framework, which justifies the extra cost for hardware-based (or hybrid) solutions.
An Extensive Review on Spectral Imaging in Biometric Systems: Challenges and Advancements
Fingerprint Presentation Attack Detection using Laser Speckle Contrast Imaging
TLDR
A fingerprint PAD method based on textural information extracted from pre-processed LSCI images, which shows that the proposed approach classifies correctly all bona fides, however, the LSCi technology experiences difficulties with thin and transparent overlay attacks.
On the vulnerability of extended Multispectral face recognition systems towards presentation attacks
TLDR
This study reveals the vulnerability of extended Multispectral face recognition system with respect to the print attack and evaluates the state-of-the-art PAD algorithms that are widely employed in conventional face PAD systems.
A New Multi-spectral Iris Acquisition Sensor for Biometric Verification and Presentation Attack Detection
TLDR
Experimental results demonstrate that the newly developed sensor indicates reliable and robust performance for both verification and PAD making it a strong candidate sensor for real-life deployment with integrated PAD.
...
...