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

• Published in: Sensors (Basel, Switzerland) Vol. 19; no. 2; p. 410
• Main Authors: Nguyen, Dat Tien, Pham, Tuyen Danh, Lee, Min Beom, Park, Kang Ryoung
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 20.01.2019; MDPI
• Subjects: Algorithms; Artificial intelligence; Biometric recognition systems; Biometrics; Cameras; Classification; Computer Security; Datasets; Face recognition; Facial Recognition; Facial recognition technology; handcrafted features; Humans; Image detection; Image enhancement; Image Processing, Computer-Assisted; Libraries; Light; Methods; Neural networks; Neural Networks (Computer); Pattern recognition; Pattern Recognition, Automated - methods; Photography - instrumentation; Recurrent neural networks; spatial and temporal information; Spatial data; stacked convolutional neural network (CNN)-recurrent neural network (RNN); Time Factors; visible-light camera sensor-based presentation attack detection; United States > US; face recognition; visible-light camera sensor-based presentation attack detection; spatial and temporal information; handcrafted features; stacked convolutional neural network (CNN)-recurrent neural network (RNN)
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s19020410

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.