Transfer learning using deep neural networks for Ear Presentation Attack Detection: New Database for PAD
This work addresses the problem of securing ear recognition systems against spoofing attacks for biometric applications, though it is incremental as it applies existing transfer learning techniques to a new domain.
The authors tackled the lack of publicly available datasets for ear presentation attack detection (PAD) by releasing a new dataset (WUT-Ear V1.0) with over 17,000 images and proposed a transfer learning method using deep neural networks, achieving 99.83% accuracy and 0.08% error rates on replay-attack data.
Ear recognition system has been widely studied whereas there are just a few ear presentation attack detection methods for ear recognition systems, consequently, there is no publicly available ear presentation attack detection (PAD) database. In this paper, we propose a PAD method using a pre-trained deep neural network and release a new dataset called Warsaw University of Technology Ear Dataset for Presentation Attack Detection (WUT-Ear V1.0). There is no ear database that is captured using mobile devices. Hence, we have captured more than 8500 genuine ear images from 134 subjects and more than 8500 fake ear images using. We made replay-attack and photo print attacks with 3 different mobile devices. Our approach achieves 99.83% and 0.08% for the half total error rate (HTER) and attack presentation classification error rate (APCER), respectively, on the replay-attack database. The captured data is analyzed and visualized statistically to find out its importance and make it a benchmark for further research. The experiments have been found out a secure PAD method for ear recognition system, publicly available ear image, and ear PAD dataset. The codes and evaluation results are publicly available at https://github.com/Jalilnkh/KartalOl-EAR-PAD.