作者: Luis Filipe A Pereira , Hector NB Pinheiro , Jose Ivson S Silva , Anderson G Silva , Thais ML Pina
DOI: 10.1109/IJCNN.2012.6252582
关键词:
摘要: We introduce a fingerprint spoof detection technique based on MLP and SVM that combines several features. The proposed is evaluated two scenarios: (i) when an impostor can perform consecutive attempts to be considered authentic; and, (ii) the system deals with fingerprints from elderly people. In order analyze these scenarios, database was developed. results show combination of features increases performance in at least 33.56% average error as more for acceptance are allowed. classifier presents better almost all tested configurations. However, accurate biometrics