Visible/Infrared face spoofing detection using texture descriptors

With extensive applications of face recognition technologies, face anti-spoofing played an important role and has drawn a great attention in the security systems. This study represents a multi-spectral face anti-spoofing method working with both visible (VIS) and near-infrared (NIR) spectra imaging. Spectral imaging is the capture of images in multiple bands. Since these attacks are carried out at the sensor, operating in the visible range, a sensor operating in another band can give more cues regarding the artifact or disguise used to carry out the attack. Our experimental results of public datasets proved that the proposed algorithms gain promising results for different testing scenarios and that our methods can deal with different illuminations and both photo and screen spoofing.

Download Full-text

Multispectral face spoofing detection using VIS–NIR imaging correlation

International Journal of Wavelets Multiresolution and Information Processing ◽

10.1142/s0219691318400039 ◽

2018 ◽

Vol 16 (02) ◽

pp. 1840003 ◽

Cited By ~ 3

Author(s):

Xudong Sun ◽

Lei Huang ◽

Changping Liu

Keyword(s):

Face Recognition ◽

Near Infrared ◽

Experimental Results ◽

Security Systems ◽

Local Descriptors ◽

Confidence Factor ◽

Nir Imaging ◽

Spoofing Detection ◽

Factor Map ◽

Face Spoofing

With the wide applications of face recognition techniques, spoofing detection is playing an important role in the security systems and has drawn much attention. This research presents a multispectral face anti-spoofing method working with both visible (VIS) and near-infrared (NIR) spectra imaging, which exploits VIS–NIR image consistency for spoofing detection. First, we use part-based methods to extract illumination robust local descriptors, and then the consistency is calculated to perform spoofing detection. In order to further exploit multispectral correlation in local patches and to be free from manually chosen regions, we learn a confidence factor map for all the patches, which is used in final classifier. Experimental results of self-collected datasets, public Msspoof and PolyU-HSFD datasets show that the proposed approach gains promising results for both intra-dataset and cross-dataset testing scenarios, and that our method can deal with different illumination and both photo and screen spoofing.

Download Full-text

Context based face spoofing detection using active near-infrared images

2016 23rd International Conference on Pattern Recognition (ICPR) ◽

10.1109/icpr.2016.7900303 ◽

2016 ◽

Author(s):

Xudong Sun ◽

Lei Huang ◽

Changping Liu

Keyword(s):

Near Infrared ◽

Infrared Images ◽

Spoofing Detection ◽

Face Spoofing

Download Full-text

Deep Discriminative Restricted Boltzmann Machine (DDRBM) for Robust Face Spoofing Detection

Progress in Human Computer Interaction ◽

10.18063/phci.v1i3.893 ◽

2018 ◽

Vol 1 (3) ◽

Author(s):

Gustavo Botelho de Souza ◽

Joao Paulo Papa ◽

Aparecido Nilceu Marana

Keyword(s):

Neural Networks ◽

Face Recognition ◽

Attack Detection ◽

Restricted Boltzmann Machine ◽

Digital Cameras ◽

Boltzmann Machine ◽

Robust Solution ◽

Spoofing Detection ◽

Recognition Systems ◽

Face Spoofing

Biometrics emerged as a robust solution for security systems. Despite, nowadays criminals are developing techniques to accurately simulate biometric traits of valid users, process known as spoofing attack, in order to circumvent the biometric applications. Face is among the main biometric characteristics, being extremely convenient for users given its non-intrusive capture by means of digital cameras. However, face recognition systems are the ones that most suffer with spoofing attacks since such cameras, in general, can be easily fooled with common printed photographs. In this sense, countermeasure techniques should be developed and integrated to the traditional face recognition systems in order to prevent such frauds. Among the main neural networks for face spoofing detection is the discriminative Restricted Boltzmann Machine (RBM) which, besides of efficiency, achieves great results in attack detection by learning the distributions of real and fake facial images. However, it is known that deeper neural networks present better accuracy results in many tasks. In this context, we propose a novel model called Deep Discriminative Restricted Boltzmann Machine (DDRBM) applied to face spoofing detection. Results on the NUAA dataset show a significative improvement in performance when compared to the accuracy rates of a traditional discriminative RBM on attack detection.

Download Full-text

SADG: Self-Aligned Dual NIR-VIS Generation for Heterogeneous Face Recognition

Applied Sciences ◽

10.3390/app11030987 ◽

2021 ◽

Vol 11 (3) ◽

pp. 987

Author(s):

Pengcheng Zhao ◽

Fuping Zhang ◽

Jianming Wei ◽

Yingbo Zhou ◽

Xiao Wei

Keyword(s):

Face Recognition ◽

Near Infrared ◽

External Information ◽

Significant Alignment ◽

Heterogeneous Face Recognition ◽

Image Translation ◽

Challenging Tasks ◽

The Mean ◽

Ablation Study ◽

Public Datasets

Heterogeneous face recognition (HFR) has aroused significant interest in recent years, with some challenging tasks such as misalignment problems and limited HFR data. Misalignment occurs among different modalities’ images mainly because of misaligned semantics. Although recent methods have attempted to settle the low-shot problem, they suffer from the misalignment problem between paired near infrared (NIR) and visible (VIS) images. Misalignment can bring performance degradation to most image-to-image translation networks. In this work, we propose a self-aligned dual generation (SADG) architecture for generating semantics-aligned pairwise NIR-VIS images with the same identity, but without the additional guidance of external information learning. Specifically, we propose a self-aligned generator to align the data distributions between two modalities. Then, we present a multiscale patch discriminator to get high quality images. Furthermore, we raise the mean landmark distance (MLD) to test the alignment performance between NIR and VIS images with the same identity. Extensive experiments and an ablation study of SADG on three public datasets show significant alignment performance and recognition results. Specifically, the Rank1 accuracy achieved was close to 99.9% for the CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS and BUAA VIS-NIR datasets, respectively.

Download Full-text

Mining discriminative patches for script identification in natural scene images

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-200260 ◽

2021 ◽

Vol 40 (1) ◽

pp. 551-563

Author(s):

Liqiong Lu ◽

Dong Wu ◽

Ziwei Tang ◽

Yaohua Yi ◽

Faliang Huang

Keyword(s):

Neural Networks ◽

Experimental Results ◽

The Other ◽

Natural Scene ◽

Fixed Size ◽

Script Identification ◽

Aspect Ratios ◽

Novel Approach ◽

Public Datasets ◽

Natural Scene Images

This paper focuses on script identification in natural scene images. Traditional CNNs (Convolution Neural Networks) cannot solve this problem perfectly for two reasons: one is the arbitrary aspect ratios of scene images which bring much difficulty to traditional CNNs with a fixed size image as the input. And the other is that some scripts with minor differences are easily confused because they share a subset of characters with the same shapes. We propose a novel approach combing Score CNN, Attention CNN and patches. Attention CNN is utilized to determine whether a patch is a discriminative patch and calculate the contribution weight of the discriminative patch to script identification of the whole image. Score CNN uses a discriminative patch as input and predict the score of each script type. Firstly patches with the same size are extracted from the scene images. Secondly these patches are used as inputs to Score CNN and Attention CNN to train two patch-level classifiers. Finally, the results of multiple discriminative patches extracted from the same image via the above two classifiers are fused to obtain the script type of this image. Using patches with the same size as inputs to CNN can avoid the problems caused by arbitrary aspect ratios of scene images. The trained classifiers can mine discriminative patches to accurately identify some confusing scripts. The experimental results show the good performance of our approach on four public datasets.

Download Full-text

Enhancing sub-bandgap external quantum efficiency by photomultiplication for narrowband organic near-infrared photodetectors

Nature Communications ◽

10.1038/s41467-021-24500-2 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Jonas Kublitski ◽

Axel Fischer ◽

Shen Xing ◽

Lukasz Baisinger ◽

Eva Bittrich ◽

...

Keyword(s):

Charge Transfer ◽

Quantum Efficiency ◽

External Quantum Efficiency ◽

Near Infrared ◽

Optical Cavity ◽

Hole Injection ◽

Visible Range ◽

Absorption Region ◽

Electromagnetic Signals ◽

Organic Photodetectors

AbstractDetection of electromagnetic signals for applications such as health, product quality monitoring or astronomy requires highly responsive and wavelength selective devices. Photomultiplication-type organic photodetectors have been shown to achieve high quantum efficiencies mainly in the visible range. Much less research has been focused on realizing near-infrared narrowband devices. Here, we demonstrate fully vacuum-processed narrow- and broadband photomultiplication-type organic photodetectors. Devices are based on enhanced hole injection leading to a maximum external quantum efficiency of almost 2000% at −10 V for the broadband device. The photomultiplicative effect is also observed in the charge-transfer state absorption region. By making use of an optical cavity device architecture, we enhance the charge-transfer response and demonstrate a wavelength tunable narrowband photomultiplication-type organic photodetector with external quantum efficiencies superior to those of pin-devices. The presented concept can further improve the performance of photodetectors based on the absorption of charge-transfer states, which were so far limited by the low external quantum efficiency provided by these devices.

Download Full-text