Visible-Light Camera Sensor-Based Presentation Attack Detection for Face Recognition by Combining Spatial and Temporal Information

Abstract

Face-based biometric recognition systems that can recognize human faces are widely employed in places such as airports, immigration offices, and companies, and applications such as mobile phones. However, the security of this recognition method can be compromised by attackers (unauthorized persons), who might bypass the recognition system using artificial facial images. In addition, most previous studies on face presentation attack detection have only utilized spatial information. To address this problem, we propose a visible-light camera sensor-based presentation attack detection that is based on both spatial and temporal information, using the deep features extracted by a stacked convolutional neural network (CNN)-recurrent neural network (RNN) along with handcrafted features. Through experiments using two public datasets, we demonstrate that the temporal information is sufficient for detecting attacks using face images. In addition, it is established that the handcrafted image features efficiently enhance the detection performance of deep features, and the proposed method outperforms previous methods.

Presentation Attack Face Image Generation Based on a Deep Generative Adversarial Network

“…As explained in Section 1, researchers have paid much attention to developing face-PAD systems to detect PA samples from face recognition systems to enhance their security [6][7][8][9][10][11][12][13][14][15]. Initially, they used several handcrafted image feature extraction methods to extract image features and detect PA samples by applying some classification method based on the extracted image features [6,8,10,11].…”

“…This type of biometric is based on the fact that facial appearance can be used to easily distinguish people. To prevent attackers, presentation attack detection for face recognition (face-PAD) systems have been proposed; these typically use a collection of real and presentation attack (PA) face images to train a detection model [6][7][8][9][10][11][12][13][14][15]. The performance of such face-PAD systems has been shown to be strongly dependent on the training data, in which PA images are captured by simulating several limited types of attacking methods, such as the use of a photo, video display, or mask.…”

Face Recognition Systems: A Survey

“…This layer basically reduces the number of parameters and computation in the network, controlling over fitting by progressively reducing the spatial size of the network. There are two operations in this layer: average pooling and maximum pooling: Various variants of neural networks have been developed in the last years, such as convolutional neural networks (CNN) [14,110] and recurrent neural networks (RNN) [111], which very effective for image detection and recognition tasks. CNNs are a very successful deep model and are used today in many applications [112].…”

“…Yim et al [124] propose a new deep architecture based on a novel type of multitask learning, which can achieve superior performance in rotating to a target-pose face image from an arbitrary pose and illumination image while preserving identity. Nguyen et al [111] propose a new approach for detecting presentation attack face images to enhance the security level of a face recognition system. The objective of this study was the use of a very deep stacked CNN-RNN network to learn the discrimination features from a sequence of face images.…”

“…Deep learning (DL): a very broad concept, which means that it has no exact definition, but studies [14,[110][111][112][113]121,130,131] agree that DL includes a set of algorithms that attempt to model high level abstractions, by modeling multiple processing layers. This field of research began in the 1980s and is a branch of automatic learning where algorithms are used in the formation of deep neural networks (DNN) to achieve greater accuracy than other classical techniques.…”