Live face detection based on the analysis of Fourier spectra

By Jiangwei Li, Yunhong Wang, Tien-Ping Tan, Anil K. Jain. SPIE Defense + Commercial Sensing, 2004

457 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/2c6eb54b11f998647cdb3838b3e59349de558f24

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

Competition on counter measures to 2-D facial spoofing attacks (2011, background): “[15] detect print-attacks by exploiting differences in the 2-D Fourier spectra of hard-copies of faces and realaccesses.”
Biometric Template Security (2008, background): “A number of efforts have been made in developing hardware as well as software solutions that are capable of performing liveness detection [18–26].”
Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues (2020, background): “Fortunately, these artifacts can be captured in frequency domain, as many prior studies suggested [58,38,32,19,57], in the form of unusual frequency distributions when compared with real faces.”
Face liveness detection by learning multispectral reflectance distributions (2011, background): “It is also noticed that some researchers attempt to detect liveness from a single image [9], [10].”
Spoofing Face Recognition With 3D Masks (2014, background): “It is relatively simple to forge such an attack for facial recognition systems, due to the fact that the photographs or videos of a valid user can be easily captured from a distance or obtained via internet, e.g. through social networks.”
Spoofing in 2D face recognition with 3D masks and anti-spoofing with Kinect (2013, methodology): “Finally, in the third group of methods, the texture of the face image is examined to find spoofing clues like printing artifacts [3] and/or blurring [13].”
50 years of biometric research: Accomplishments, challenges, and opportunities (2016, unknown): “The early iris cameras such as the one developed by Daugman and other commercial cameras developed in the 1990s were not only bulky and expensive, but also required high levels of cooperation from the user to provide good quality iris images (see Fig.”
Security evaluation of biometric authentication systems under real spoofing attacks (2012, background): “The issue of spooﬁng attacks has been especially studied in the case of ﬁngerprints and faces, and, rarely, on other biometrics, in the novel research ﬁeld of biometric liveness detection [11, 20, 9, 10, 23, 33, 22, 21, 34, 4, 6].”
Face liveness detection with component dependent descriptor (2013, methodology): “Li et al. [15] pro-978-1-4799-0310-8 posed a method based on the analysis of Fourier spectra.”
Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning (2020, background): “An early work on face PAD by Li et al. [28] used Fourier spectra analysis to capture the difference between the live and spoof face images.”
Presentation Attack Detection for Face Recognition Using Light Field Camera (2015, methodology): “In addition to these schemes, frequency analysis based schemes also exist that use 2D Fast Fourier Transform (FFT) to identify the face presentation attacks [2].”
Face De-Spoofing: Anti-Spoofing via Noise Modeling (2018, background): “To overcome some of these difﬁculties, researchers tackle the problem in different domains, such as HSV and YCbCr color space [24,25], temporal domain [26,27,28,29] and Fourier spectrum [30].”
Face Anti-Spoofing: Model Matters, so Does Data (2019, background): “Features in the frequency domain were also studied in [22].”
Biometric Antispoofing Methods: A Survey in Face Recognition (2014, methodology): “The vast majority of feature-level static methods are based on the analysis of the face texture using different image processing tools such as: the Fourier Spectrum [144]; multiple Difference of Gaussian (DoG) filters to extract specific frequency information [105] which has also been combined with ”
Learn Convolutional Neural Network for Face Anti-Spoofing (2014, methodology): “1) Texture-based Anti-Spooﬁng: In [22], Li et al. proposed a method based on the analysis of Fourier spectra.”
Face spoofing detection from single images using micro-texture analysis (2011, methodology): “[6] described a method for detecting print-attack face spoofing.”
CASIA-SURF: A Large-Scale Multi-Modal Benchmark for Face Anti-Spoofing (2019, methodology): “To improve the robustness to illumination variation, some algorithms adopt HSV and YCbCr color spaces [6], [7], as well as Fourier spectrum [33].”