作者: Yosep Park , Unsoo Jang , Eui Chul Lee
DOI: 10.1007/S00500-017-2707-3
关键词: Fingerprint recognition 、 Pattern recognition 、 Skewness 、 Biometrics 、 Fingerprint (computing) 、 Artificial intelligence 、 Mathematics 、 Support vector machine 、 Kurtosis 、 Spoofing attack 、 Feature (machine learning)
摘要: Recently, attempts at spoofing biometric fingerprint recognition systems through fake fingerprints have been frequently reported. Most existing detection methods require either additional sensors or complicated calculations. In this paper, a method is proposed that employs combinations of six simple statistical moment features. These features are deviation, variance, skewness, kurtosis, hyperskewness, and hyperflatness the fingerprints. addition, average brightness, standard differential considered. Of all features, best ones selected in terms overlap ratio between real images. The multi-dimensional combined feature level support vector machine. Based on experimental results, showed classification accuracy approximately 99%.