Enhancing computer vision to detect face spoofing attack utilizing a single frame from a replay video attack using deep learning

Alotaibi, Aziz; Mahmood, Ausif

doi:10.1109/optip.2016.7528488

Cited by 22 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An evaluation of several IQA techniques was done in [34].Several studies have tested the efficacy of dynamic texture analysis in liveness detection in [35][36][37][38][39][40][41][42][43]. Static texture analysis on the other hand have been explored through large number of published studies in our research period in [4,[44][45][46][47][48][49][50][51][52][53][54][55][56][57][58]].…”

Section: Texture Analysismentioning

confidence: 99%

Insight on face liveness detection: A systematic literature review

Raheem¹,

Ahmad²,

Adnan³

2019

IJECE

View full text Add to dashboard Cite

<p>To review researcher’s attempts in response to the problem of spoofing and liveness detection, mapping the research overview from the literature survey into a suitable taxonomy, exploring the basic properties of the field, motivation of using liveness detection methods in face recognition, and Problems that may restrain the advantages. We presented a subjected search on face recognition with liveness detection and its synonyms in four main databases: Web of science, Science Direct, Scopus and IEEE Xplore. We believe that these databases are widely inclusive enough to cover the literature.<em> </em>The final number of articles considered is 65 articles. 4 of them where review and survey articles that described a general overview about liveness detection and anti-spoofing methods. Since 2012, and despite of leaving some areas unestablished and needs more attention, researchers tried to keep track of liveness detection in several ways. No matter what their category is, articles concentrated on challenges that faces the full utility of anti-spoofing methods and recommended some solutions to overcome these challenges. In this paper, different types of liveness detection and face anti-spoofing techniques are investigated to keep researchers updated with what is being developed in this field.</p>

show abstract

Section: Texture Analysismentioning

confidence: 99%

Insight on face liveness detection: A systematic literature review

Raheem¹,

Ahmad²,

Adnan³

2019

IJECE

View full text Add to dashboard Cite

show abstract

“…Recently, deep neural network‐based approaches have become an efficient tool for anti‐spoofing systems –. In particular, deep convolutional neural network (D‐CNN) architecture is the most widely used discriminative feature learning from 2D images.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, deep neural network-based approaches have become an efficient tool for anti-spoofing systems. 11,21,22,[40][41][42][43][44] In particular, deep convolutional neural network (D-CNN) architecture is the most widely used discriminative feature learning from 2D images. Since the results are so encouraging, it becomes a new trend in face anti-spoofing research community.…”

Section: Related Workmentioning

confidence: 99%

Cover patches: A general feature extraction strategy for spoofing detection

Cai

Leng

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Face anti‐spoofing has attracted many attentions in security applications, such as mobile payment and entrance guard. Until now, face anti‐spoofing technique is still a challenging task. Mainstream image‐based spoofing algorithms usually use global motion or texture information to distinguish whether an input face is live or fake. However, the performance of these methods are sensitive in light changes, or images acquired from different sensors. The main reason is that spoofed face image always has slight different texture in local areas, such as landmark or salient region of face. To this end, this paper proposes a novel multi‐patches feature extraction strategy to detect spoofing. First, a set of patches with specific combination scheme is selected to cover the face image. Second, features such as hand‐crafted Gray Level Co‐occurrence Matrix (GLCM), Local Binary Patterns (LBP), or deep features are extracted from these patches. Third, all features are combined as the global descriptor of the face image, then fed into an SVM classifier to verify the anti‐spoofing detection. Experimental results show that the proposed strategy can effectively enhance the performance, concerning with the accuracy of spoofed face detection in four widely used anti‐spoofing databases.

show abstract

“…Lai and Tai [15] recently proposed a liveness test against attacks by fake images or videos displayed on HD screens by analyzing the chrominance characteristics and the saturation of the face recognition system's input images. Convolutional neural networks have also been recently employed to assist anti-spoofing techniques as in [16] where the classifier is trained to distinguish between live faces and imposter images from their differences in the edge patterns and the surface textures in single frames of video sequences.…”

Section: Related Workmentioning

confidence: 99%

Designing a Facial Spoofing Database for Processed Image Attacks

Omar¹,

Ivrissimtzis²

2016

7th International Conference on Imaging for Crime Detection and Prevention (ICDP 2016)

View full text Add to dashboard Cite

Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-pro t purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. AbstractFace recognition systems are used for user authentication in everyday applications such as logging into a laptop or smartphone without need to memorize a password. However, they are still vulnerable to spoofing attacks, as for example when an imposter gains access to a system by holding a printed photo of the rightful user in front of the camera. In this paper we are concerned with the design of face image databases for evaluating the performance of anti-spoofing algorithms against such attacks. We present a new database, supporting testing against an enhancement of the attack, where the imposter processes the stolen image before printing it. By testing a standard antispoofing algorithm on the new database we show a significant decrease in its performance and, as a simple remedy to this problem, we propose the inclusion of processed imposter images into the training set.

show abstract

Enhancing computer vision to detect face spoofing attack utilizing a single frame from a replay video attack using deep learning

Cited by 22 publications

References 15 publications

Insight on face liveness detection: A systematic literature review

Insight on face liveness detection: A systematic literature review

Cover patches: A general feature extraction strategy for spoofing detection

Designing a Facial Spoofing Database for Processed Image Attacks

Contact Info

Product

Resources

About