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

Abstract

Although face-based biometric recognition systems have been widely used in many applications, this type of recognition method is still vulnerable to presentation attacks, which use fake samples to deceive the recognition system. To overcome this problem, presentation attack detection (PAD) methods for face recognition systems (face-PAD), which aim to classify real and presentation attack face images before performing a recognition task, have been developed. However, the performance of PAD systems is limited and biased due to the lack of presentation attack images for training PAD systems. In this paper, we propose a method for artificially generating presentation attack face images by learning the characteristics of real and presentation attack images using a few captured images. As a result, our proposed method helps save time in collecting presentation attack samples for training PAD systems and possibly enhance the performance of PAD systems. Our study is the first attempt to generate PA face images for PAD system based on CycleGAN network, a deep-learning-based framework for image generation. In addition, we propose a new measurement method to evaluate the quality of generated PA images based on a face-PAD system. Through experiments with two public datasets (CASIA and Replay-mobile), we show that the generated face images can capture the characteristics of presentation attack images, making them usable as captured presentation attack samples for PAD system training.

Enhanced Image-Based Endoscopic Pathological Site Classification Using an Ensemble of Deep Learning Models

“…Recently, with the development of learning-based techniques, deep learning has been widely used in computer vision research. This technique has been successfully applied to various computer vision/pattern recognition problems such as image classification [ 23 , 24 , 25 , 26 , 27 ], object detection [ 32 , 33 ], and image generation [ 34 , 35 , 36 ]. The success of deep learning comes from the fact that this technique simulates the way in which the human brain processes information (images).…”

Weakly Supervised Learning for Transmission Line Detection Using Unpaired Image-to-Image Translation

“…Zhu et al [27] proposed CycleGAN, which translates images from the source domain to the target domain with the cycle consistency loss, and this method shows remarkable results in the style transfer task. Researchers have extended unpaired image-to-image translation for several applications [51][52][53][54][55][56][57][58] to address issues such as data imbalance, lack of diversity, and limitation in collecting real paired dataset.…”

“…To prepare for such a presentation attack detection (PAD), Nguyen et al [55] generalized the model to fake presentation attack face images obtained via CycleGAN. Inspired by these studies, we employed the image-to-image translation to refine the localization mask using pseudo-line data, and the effectiveness of a refinement network is shown in an ablation study later on.…”

IriTrack

“…However, a large body of research has demonstrated the vulnerability of face recognition systems against presentation attacks, where an adversary attempts to subvert a recognition system by presenting a facial artefact, which mimics facial biometric features of a legitimate user [8,24,27,28]. Based on the artefact used, typical 2D facial presentation attacks involve three categories: printed photo attacks, electronic facial image attacks, and facial video attacks [7,11,17,19,33].…”