Face anti-spoofing with multifeature videolet aggregation
01 Dec 2016-pp 1035-1040
TL;DR: A novel multi-feature evidence aggregation method for face spoofing detection that fuses evidence from features encoding of both texture and motion properties in the face and also the surrounding scene regions and provides robustness to different attacks.
Abstract: Biometric systems can be attacked in several ways and the most common being spoofing the input sensor. Therefore, anti-spoofing is one of the most essential prerequisite against attacks on biometric systems. For face recognition it is even more vulnerable as the image capture is non-contact based. Several anti-spoofing methods have been proposed in the literature for both contact and non-contact based biometric modalities often using video to study the temporal characteristics of a real vs. spoofed biometric signal. This paper presents a novel multi-feature evidence aggregation method for face spoofing detection. The proposed method fuses evidence from features encoding of both texture and motion (liveness) properties in the face and also the surrounding scene regions. The feature extraction algorithms are based on a configuration of local binary pattern and motion estimation using histogram of oriented optical flow. Furthermore, the multi-feature windowed videolet aggregation of these orthogonal features coupled with support vector machine-based classification provides robustness to different attacks. We demonstrate the efficacy of the proposed approach by evaluating on three standard public databases: CASIA-FASD, 3DMAD and MSU-MFSD with equal error rate of 3.14%, 0%, and 0%, respectively.
Citations
More filters
TL;DR: Wang et al. as discussed by the authors proposed a temporal transformer network (TTN) to learn multi-granularity temporal characteristics for face anti-spoofing, which mainly consists of temporal difference attentions (TDA), a pyramid temporal aggregation (PTA), and a temporal depth difference loss (TDL).
Abstract: Face anti-spoofing (FAS) is essential for securing face recognition systems. Despite the decent performance, few existing works fully leverage temporal information. This would inevitably lead to inferior performance because real and fake faces tend to share highly similar spatial appearances, while important temporal features between consecutive frames are neglected. In this work, we propose a temporal transformer network (TTN) to learn multi-granularity temporal characteristics for FAS. It mainly consists of temporal difference attentions (TDA), a pyramid temporal aggregation (PTA), and a temporal depth difference loss (TDL). Firstly, the vision transformer (ViT) is used as the backbone where comprehensive local patches are utilized to provide subtle differences between live and spoof faces. Then, instead of learning temporal features on global faces which may miss some important local cues, the TDA is developed to extract motion-sensitive cues on each of the comprehensive local patches. Moreover, the TDA is inserted into different layers of the ViT, learning multi-scale motion-sensitive local cues to improve the FAS performance. Secondly, it is observed that different subjects may have different visual tempos in some actions, making it necessary to model different temporal speeds. Our PTA aggregates temporal features at various tempos, which could build short-range and long-range relations among multiple frames. Thirdly, depth maps for real parts may change continuously, while they remain zeros for spoof regions. In order to locate motion features on facial parts, the TDL is proposed to guide the network to locate spoof facial parts where motion patterns between neighboring frames are set as the ground truth. To the best of our knowledge, this work is the first attempt to learn temporal characteristics via transformers. Both qualitative and quantitative results on several challenging tasks demonstrate the usefulness and effectiveness of our proposed methods.
15 citations
TL;DR: The experimental results show that the introduction of the proposed perturbation layer in the CNN improved the face PAD performance, in both intra-database and cross-database scenarios.
14 citations
Cites methods from "Face anti-spoofing with multifeatur..."
...In cross-database scenarios, we perform comparison with the following state-of-the-art approaches: 374 LBP-TOP[25] , color texture [57], visual-codebook [58], Videolet aggregation [59], domain 375 adaption [60], De-spoof [47], Auxiliary [19], deep dynamic textures [61], DDGL [45], GFA-CNN 376 [62], STASN [63]....
[...]
04 Jun 2019
TL;DR: For the first time in the literature, it is possible to "fool" the PAD algorithms using adversarial perturbations using convolutional autoencoder to learn the perturbation network.
Abstract: Face recognition systems are vulnerable to presentation attacks such as replay and 3D masks. In the literature, several presentation attack detection (PAD) algorithms are developed to address this problem. However, for the first time in the literature, this paper showcases that it is possible to "fool" the PAD algorithms using adversarial perturbations. The proposed perturbation approach attacks the presentation attack detection algorithms at the PAD feature level via transformation of features from one class (attack class) to another (real class). The PAD feature tampering network utilizes convolutional autoencoder to learn the perturbations. The proposed algorithm is evaluated with respect to CNN and local binary pattern (LBP) based PAD algorithms. Experiments on three databases, Replay, SMAD, and Face Morph, showcase that the proposed approach increases the equal error rate of PAD algorithms by at least two times. For instance, on the SMAD database, PAD equal error rate (EER) of 20.1% is increased to 55.7% after attacking the PAD algorithm.
14 citations
Cites background from "Face anti-spoofing with multifeatur..."
...The results related to face presentation attack detection using original and tampered LBP features are summarized in Table 2....
[...]
...Since some PAD algorithms are handcrafted in nature, we also performed some of the experiments with LBP based PAD algorithms....
[...]
...The LBP image is formed by comparing the center pixel of each 3 × 3 grid of the image from its 8 neighborhood pixels....
[...]
...Texture based algorithms such as Gaussian [27], LBP [19, 23], Gabor, Histogram of Oriented Gradients (HOG), Wavelet+ Haralick [1] are the most popular and provide state-of-the-art (SOTA) detection performances across various types of databases....
[...]
...LBP-based PAD Algorithm [9, 19]: The traditional LBP histogram features are computed both from the real and spoof images....
[...]
01 Jul 2018
TL;DR: By combining intra-channel based facial texture and CCoLBP feature, the differences of color distortion and texture distribution between the real faces and the artefacts are characterized and the detection is accomplished by using a Softmax classifier.
Abstract: To counter face presentation attack in face recognition system, the chromatic facial texture differences between the real faces and the facial artefacts are fully analyzed, and chromatic co-occurrence of local binary pattern (CCoLBP) is proposed to investigate the inter-channel based information. Based on the principle of presentation attack and its influence on color component of the face image, a face presentation attack detection (PAD) scheme based on CCoLBP is proposed. By combining intra-channel based facial texture and CCoLBP feature, the differences of color distortion and texture distribution between the real faces and the artefacts are characterized. With these features, the detection is accomplished by using a Softmax classifier. Experiments are done with 5 public databases, and the experimental results and analysis indicate the effectiveness of CCoLBP, and it can achieve good performance in cross-database testing. It has great potential in the application of face PAD with real-time requirement.
13 citations
28 Oct 2019
TL;DR: This work contemplates low-power devices through the combination of Fourier transforms, different classification methods, and low-level feature descriptors to estimate whether probe samples correspond to spoofing attacks, and claims to be the first approach associating features extracted from both spatial and frequency domains.
Abstract: A face spoofing attack occurs when an intruder attempts to impersonate someone with a desirable authentication clearance. To detect such intrusions, many researchers have dedicated their efforts to study visual liveness detection as the primary indicator to block spoofing violations. In this work, we contemplate low-power devices through the combination of Fourier transforms, different classification methods, and low-level feature descriptors to estimate whether probe samples correspond to spoofing attacks. The proposed method has low-computational cost and, to the best of our knowledge, this is the first approach associating features extracted from both spatial and frequency domains. We conduct experiments with embeddings of Support Vector Machines and Partial Least Squares on recent and well-known datasets under same and cross-database settings. Results show that, even though devised towards resource-limited single-board computers, our approach is able to achieve significant results, outperforming state-of-the-art methods.
13 citations
Cites methods from "Face anti-spoofing with multifeatur..."
...On cross-datasets evaluations, it is customary to employ Half Total Error Rate, hter = far+frr 2 , which is half the sum of the False Rejection Rate (frr) and the False Acceptance Rate (far) [14, 23]....
[...]
References
More filters
TL;DR: A novel approach for recognizing DTs is proposed and its simplifications and extensions to facial image analysis are also considered and both the VLBP and LBP-TOP clearly outperformed the earlier approaches.
Abstract: Dynamic texture (DT) is an extension of texture to the temporal domain. Description and recognition of DTs have attracted growing attention. In this paper, a novel approach for recognizing DTs is proposed and its simplifications and extensions to facial image analysis are also considered. First, the textures are modeled with volume local binary patterns (VLBP), which are an extension of the LBP operator widely used in ordinary texture analysis, combining motion and appearance. To make the approach computationally simple and easy to extend, only the co-occurrences of the local binary patterns on three orthogonal planes (LBP-TOP) are then considered. A block-based method is also proposed to deal with specific dynamic events such as facial expressions in which local information and its spatial locations should also be taken into account. In experiments with two DT databases, DynTex and Massachusetts Institute of Technology (MIT), both the VLBP and LBP-TOP clearly outperformed the earlier approaches. The proposed block-based method was evaluated with the Cohn-Kanade facial expression database with excellent results. The advantages of our approach include local processing, robustness to monotonic gray-scale changes, and simple computation
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....
[...]
IBM1
TL;DR: The inherent strengths of biometrics-based authentication are outlined, the weak links in systems employing biometric authentication are identified, and new solutions for eliminating these weak links are presented.
Abstract: Because biometrics-based authentication offers several advantages over other authentication methods, there has been a significant surge in the use of biometrics for user authentication in recent years. It is important that such biometrics-based authentication systems be designed to withstand attacks when employed in security-critical applications, especially in unattended remote applications such as e-commerce. In this paper we outline the inherent strengths of biometrics-based authentication, identify the weak links in systems employing biometrics-based authentication, and present new solutions for eliminating some of these weak links. Although, for illustration purposes, fingerprint authentication is used throughout, our analysis extends to other biometrics-based methods.
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]....
[...]
01 Jan 2009
TL;DR: This thesis builds a human-assisted motion annotation system to obtain ground-truth motion, missing in the literature, for natural video sequences, and proposes SIFT flow, a new framework for image parsing by transferring the metadata information from the images in a large database to an unknown query image.
Abstract: The focus of motion analysis has been on estimating a flow vector for every pixel by matching intensities. In my thesis, I will explore motion representations beyond the pixel level and new applications to which these representations lead.
I first focus on analyzing motion from video sequences. Traditional motion analysis suffers from the inappropriate modeling of the grouping relationship of pixels and from a lack of ground-truth data. Using layers as the interface for humans to interact with videos, we build a human-assisted motion annotation system to obtain ground-truth motion, missing in the literature, for natural video sequences. Furthermore, we show that with the layer representation, we can detect and magnify small motions to make them visible to human eyes. Then we move to a contour presentation to analyze the motion for textureless objects under occlusion. We demonstrate that simultaneous boundary grouping and motion analysis can solve challenging data, where the traditional pixel-wise motion analysis fails.
In the second part of my thesis, I will show the benefits of matching local image structures instead of intensity values. We propose SIFT flow that establishes dense, semantically meaningful correspondence between two images across scenes by matching pixel-wise SIFT features. Using SIFT flow, we develop a new framework for image parsing by transferring the metadata information, such as annotation, motion and depth, from the images in a large database to an unknown query image. We demonstrate this framework using new applications such as predicting motion from a single image and motion synthesis via object transfer. Based on SIFT flow, we introduce a nonparametric scene parsing system using label transfer, with very promising experimental results suggesting that our system outperforms state-of-the-art techniques based on training classifiers. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)
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]....
[...]
TL;DR: An efficient and rather robust face spoof detection algorithm based on image distortion analysis (IDA) that outperforms the state-of-the-art methods in spoof detection and highlights the difficulty in separating genuine and spoof faces, especially in cross-database and cross-device scenarios.
Abstract: Automatic face recognition is now widely used in applications ranging from deduplication of identity to authentication of mobile payment. This popularity of face recognition has raised concerns about face spoof attacks (also known as biometric sensor presentation attacks), where a photo or video of an authorized person’s face could be used to gain access to facilities or services. While a number of face spoof detection techniques have been proposed, their generalization ability has not been adequately addressed. We propose an efficient and rather robust face spoof detection algorithm based on image distortion analysis (IDA). Four different features (specular reflection, blurriness, chromatic moment, and color diversity) are extracted to form the IDA feature vector. An ensemble classifier, consisting of multiple SVM classifiers trained for different face spoof attacks (e.g., printed photo and replayed video), is used to distinguish between genuine (live) and spoof faces. The proposed approach is extended to multiframe face spoof detection in videos using a voting-based scheme. We also collect a face spoof database, MSU mobile face spoofing database (MSU MFSD), using two mobile devices (Google Nexus 5 and MacBook Air) with three types of spoof attacks (printed photo, replayed video with iPhone 5S, and replayed video with iPad Air). Experimental results on two public-domain face spoof databases (Idiap REPLAY-ATTACK and CASIA FASD), and the MSU MFSD database show that the proposed approach outperforms the state-of-the-art methods in spoof detection. Our results also highlight the difficulty in separating genuine and spoof faces, especially in cross-database and cross-device scenarios.
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]....
[...]
Proceedings Article•
27 Sep 2012TL;DR: This paper inspects the potential of texture features based on Local Binary Patterns (LBP) and their variations on three types of attacks: printed photographs, and photos and videos displayed on electronic screens of different sizes and concludes that LBP show moderate discriminability when confronted with a wide set of attack types.
Abstract: Spoofing attacks are one of the security traits that biometric recognition systems are proven to be vulnerable to. When spoofed, a biometric recognition system is bypassed by presenting a copy of the biometric evidence of a valid user. Among all biometric modalities, spoofing a face recognition system is particularly easy to perform: all that is needed is a simple photograph of the user. In this paper, we address the problem of detecting face spoofing attacks. In particular, we inspect the potential of texture features based on Local Binary Patterns (LBP) and their variations on three types of attacks: printed photographs, and photos and videos displayed on electronic screens of different sizes. For this purpose, we introduce REPLAY-ATTACK, a novel publicly available face spoofing database which contains all the mentioned types of attacks. We conclude that LBP, with ∼15% Half Total Error Rate, show moderate discriminability when confronted with a wide set of attack types.
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]....
[...]