Face liveness detection by learning multispectral reflectance distributions

By Zhiwei Zhang, Dong Yi, Zhen Lei, S. Li. 2011

210 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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

Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems (2016, methodology): “Fake faces (see Table 2) were obtained by displaying a photo of the targeted client on a laptop screen, or by printing it on paper, and then showing it to the camera [26], [27].”
Face spoofing detection from single images using micro-texture analysis (2011, background): “Multispectral images can also be used for analysing the reflectance of object surfaces and thus discriminating live faces from fake ones [14].”
Secure Face Unlock: Spoof Detection on Smartphones (2016, methodology): “Active methods utilize additional sensors, such as nearinfrared (NIR) and 3D depth to capture a face besides the 2D visual face image [24], [25].”
Robustness of multi-modal biometric verification systems under realistic spoofing attacks (2011, methodology): “So far this kind of attacks has been analysed especially for fingerprints [5, 6], but this security issue has been also pointed out for face, iris and other biometrics as well [8, 9, 10].”
Spoofing in 2D face recognition with 3D masks and anti-spoofing with Kinect (2013, background): “A similar conclusion is also made in [22].”
Learn Convolutional Neural Network for Face Anti-Spoofing (2014, background): “In [26] and [37], the authors selected proper working spectrums so that the reflectance differences between genuine and fake faces increased.”
Face Presentation Attack with Latex Masks in Multispectral Videos (2017, background): “Several algorithms have been proposed for face PAD where such attacks are easily detected [17, 22, 23].”
Face Anti-spoofing: Visual Approach (2014, background): “While multimodal analysis [23–25] and multispectral imaging [26–28] provide efficient means for discriminating real faces from fake ones, spoofing detection can be performed also based on the same data that is used for the actual face recognition process.”
Evaluation of multimodal biometric score fusion rules under spoof attacks (2012, background): “If the fused score s is below a given acceptance threshold T , the user is classified as an impostor, otherwise it is classified as a genuine user.”
Biometric Antispoofing Methods: A Survey in Face Recognition (2014, background): “However, some interesting methods have been proposed base on imaging technology outside the visual spectrum, such as: complementary infrared (IR) or near infrared (NIR) images, which are even claimed to provide sufficient information to distinguish between identical twins [129], [152]; comparing the”
A face antispoofing database with diverse attacks (2012, background): “It is important to mention that multi-spectral [7, 8, 9] and multi-modality [10, 11] based anti-spoofing methods also perform quite well by exploring other liveness clues such as face images under nonvisible illuminations or voice information.”
Context based face anti-spoofing (2013, background): “While challenge-response approach [7, 13, 16], multi-modal analysis [5, 12, 16] and multispectral imaging [22, 24, 29] provide efficient means for discriminating real faces from fake ones, they are also rather impractical due to interaction or unconventional imaging requirements.”
Face liveness detection with component dependent descriptor (2013, background): “In [20, 26], it is proved that indistinguishable faces exhibit much different properties from the genuine ones under invisible light.”
Security evaluation of biometric authentication systems under real spoofing attacks (2012, methodology): “The advent of public video sharing websites and reduction in the cost of high quality video cameras and portable devices have also made it easy to obtain or capture genuine user’s facial video samples without subject’s consent and awareness, which can be later presented to the system using a portabl”
Face Spoof Detection With Image Distortion Analysis (2015, methodology): “To evaluate the effectiveness of spoof detection algorithms, many published papers designed and tested their algorithms on proprietary spoof databases [6], [10], [11], [19].”
Biometrics Evaluation Under Spoofing Attacks (2014, background): “One possible approach, relying on the assumption that spoofing two or more modes is more difficult than spoofing a single one, [8], [9], is combining several of them.”