An Anomaly Detection Approach to Face Spoofing Detection: A New Formulation and Evaluation Protocol
An Anomaly Detection Approach to Face Spoofing Detection: A New Formulation and Evaluation Protocol
复制标题
DOI：
10.1109/access.2017.2729161
复制
发表时间：
2017-01-01
期刊：
影响因子：
3.9
通讯作者：
Christmas, William
中科院分区：
文献类型：
--
作者：
Arashloo, Shervin Rahimzadeh;Kittler, Josef;Christmas, William
人脸欺骗检测通常被公式化为两类识别问题，其中利用正样本（真实的访问）和负样本（欺骗尝试）的相关特征来训练系统。然而，欺骗攻击的多样性，欺骗攻击者的任何新手段，可能会发明（以前未被系统发现）成像传感器互操作性的问题，以及除了小样本量之外的其他环境因素使问题变得非常具有挑战性。考虑到这些意见，在本文中，一些命题的评估方案，问题的制定和解决。首先，提出了一种新的评估协议，以研究未知攻击类型的发生的影响，其中训练和测试数据是由不同的手段产生的。新的评估协议更好地反映了欺骗尝试的现实条件，攻击者可能会想出新的欺骗手段。数据库间和数据库内的实验纳入评估计划，以考虑传感器的互操作性问题。其次，提出了一个新的和更现实的配方的欺骗检测问题的异常检测的概念的基础上，训练数据只来自积极的类。当然，测试数据可能来自阳性或阴性类。这样的一类公式避免了对负训练样本可用性的需要，在交易情况下，负训练样本应该代表所有可能的欺骗类型。最后，一个全面的评估和比较20个不同的一类和两类系统的视频序列的三个广泛采用的数据库进行调查的优点，一类异常检测方法相比，常见的两类配方。它表明，基于异常的配方是不逊色于传统的两类方法相比。
Face spoofing detection is commonly formulated as a two-class recognition problem where relevant features of both positive (real access) and negative samples (spoofing attempts) are utilized to train the system. However, the diversity of spoofing attacks, any new means of spoofing attackers, may invent (previously unseen by the system) the problem of imaging sensor interoperability, and other environmental factors in addition to the small sample size make the problem quite challenging. Considering these observations, in this paper, a number of propositions in the evaluation scenario, problem formulation, and solving are presented. First of all, a new evaluation protocol to study the effect of occurrence of unseen attack types, where the train and test data are produced by different means, is proposed. The new evaluation protocol better reflects the realistic conditions in spoofing attempts where an attacker may come up with new means for spoofing. Inter-database and intra-database experiments are incorporated into the evaluation scheme to account for the sensor interoperability problem. Second, a new and more realistic formulation of the spoofing detection problem based on the anomaly detection concept is proposed where the training data come from the positive class only. The test data, of course, may come from the positive or negative class. Such a one-class formulation circumvents the need for the availability of negative training samples, which, in an in deal case, should be the representative of all possible spoofing types. Finally, a thorough evaluation and comparison of 20 different one-class and two-class systems on the video sequences of three widely employed databases is performed to investigate the merits of the one-class anomaly detection approaches compared with the common two-class formulations. It is demonstrated that the anomaly-based formulation is not inferior as compared with the conventional two-class approach.