Face anti-spoofing with multifeature videolet aggregation
Citations
109 citations
Cites background from "Face anti-spoofing with multifeatur..."
...Other works also focus on temporal features such as dynamic texture [44], micro-motion [45] and eye blinking [46]....
[...]
104 citations
Cites methods from "Face anti-spoofing with multifeatur..."
...[20] have demonstrated that applying PAD algorithm on the input face images yield better results than detected face images only....
[...]
103 citations
98 citations
Cites methods from "Face anti-spoofing with multifeatur..."
...…attack detection methodologies include software level solutions such as color texture analysis based detection (Agarwal et al. 2016; Boulkenafet et al. 2016; Siddiqui et al. 2016) and hardware level solutions such as light polarization analysis using a novel hardware extension (Rudd et al. 2016)....
[...]
90 citations
Cites background or methods from "Face anti-spoofing with multifeatur..."
...unconscious facial motions to detect photo and video attacks [3], [10], [12], [25], [45], [47]....
[...]
...Comparison Methods: Eight state-of-the-art methods related to face anti-spoofing are used for comparison in the 3DMAD and SUP datasets, which includes appearancebased methods: multi-scale LBP (MS_LBP for short) [15], Color Texture (CT for short) [6], deep features from the last fully connected layer of the CNN (fc_CNN for short) [53] and image distortion analysis (IDA for short) [51]; motionbased methods: LBPTOP [12], multifeature videolet aggregation (Videolet for short) [45], optical flow field (OFF for short) [3]; and methods based on other cues: the rPPG method [37]....
[...]
...According to the method mentioned in [45], we divide our input video into nine segments and extract the LBP and histogram of oriented optical flows (HOOF) features for each segment, which we use to train the corresponding SVM classifiers with RBF kernels....
[...]
...in [45] extracts the appearance features of LBP and the motion features of oriented optical flow for video segments....
[...]
...For testing, we use the aggregation strategy of [45] on the classification scores of the video segments from the trained classifiers to obtain a final classification score for the entire video....
[...]
References
2,653 citations
"Face anti-spoofing with multifeatur..." refers background in this paper
...Dynamic texture features such as LBP-TOP [22] are studied in this regard....
[...]
1,709 citations
"Face anti-spoofing with multifeatur..." refers background in this paper
...Biometric systems have different points of vulnerability such as sensor attacks, overriding feature extraction, tampering feature representation, corrupting matcher, tampering stored template, and overriding decision [18]....
[...]
899 citations
"Face anti-spoofing with multifeatur..." refers methods in this paper
...The orientation based optical flow vector is computed by solving the optimization problem 1 using conjugate gradient method [12]....
[...]
716 citations
"Face anti-spoofing with multifeatur..." refers background or methods in this paper
...• On MSU dataset, HOOF obtains tremendous improvement in EER (from 30.41 to 2.50...
[...]
...Similarly, at the Inter Feature Fusion stage, the correlation of 0.51, 0.62, and 0.66 is observed for CASIA, MSU, and 3DMAD datasets, respectively....
[...]
...MSU dataset contains a higher fraction of replay attack videos compared to CASIA....
[...]
...• Performance of the Proposed Approach: The proposed fusion approach (using HOOF and multi-LBP with face and scene aggregated over videolets) provides 0% EER with uncontrolled illumination and background on both MSU and 3DMAD datasets....
[...]
...Orthogonal to the LBP texture descriptors based approaches, quality assessment metrics such as specular reflection, blurring and color density are also explored for anti-spoofing [10], [20]....
[...]
707 citations
Additional excerpts
...The face anti-spoofing problem is extensively studied in literature, particularly with the introduction of Print Attack dataset [1], Replay Attack dataset [5], CASIA-FASD spoofing dataset [21], 3DMAD database [7], and MSU mobile face spoofing database [20]....
[...]