[ 1 ] [ 2 ] [ 3 ] [ 4 ] [ 5 ] [ 6 ] [ 7 ] [ 8 ] [ 9 ] [ 10 ] [ 11 ] [ 12 ] [ 13 ]

Journal of Information Science and Engineering, Vol. 37 No. 3, pp. 605-616

Anti-Spoofing of Live Face Authentication on Smartphone

1Graduate Institute of Biomedical Electronics and Bioinformatics
College of Electrical Engineering and Computer Science

2Department of Computer Science and Information Engineering
National Taiwan University
Taipei, 106 Taiwan
E-mail: r05945052@ntu.edu.tw; g104018004@smail.nchu.edu.tw; fuh@csie.ntu.edu.tw

Our proposed method is capable of authenticating the input image is from real user or spoofing attack, including paper photograph, digital photograph, and video, using only the Red, Green, Blue (RGB) frontal camera of common smart phone, without the help of depth camera or infrared thermal sensor. We first capture live faces in each frame of input video streams by single shot multi-box detector then feed into our designed convolution neural network after certain data augmentation and finally obtain a well-trained spoof face classifier. Finally, we compared to Parkin and Grinchuk’s results, using dataset CASIASURF [1], and compare the result of vgg16, InceptionNet, ResNet, DenseNet and MobileNet in CASIA-SURFT dataset.

Keywords: spoofing attack, single shot multi-box detector, data augmentation, VGG-16, stereo matching

  Retrieve PDF document (JISE_202103_07.pdf)