Liveness detection on touchless fingerprint devices using texture descriptors and artificial neural networks

This paper presents a liveness detection method based on texture descriptors and artificial neural networks, whose objective is to identify potential attempts of spoofing attacks against touchless fingerprinting devices. First, a database was created. It comprises a set of 400 images, from which 200 represent real fingers and 200 represent fake fingers made of beeswax, corn flour play dough, latex, silicone and wood glue, 40 samples each. The artificial neural network classifier is trained and tested in 7 different scenarios. In Scenario 1, there are only two classes, “real finger” and “fake finger”. From Scenarios 2 to 6, six classes are used, but classification is done considering the “realfinger” class and each one of the five “fake finger” classes, separately. Finally, in Scenario 7, six classes are used and the classifier must indicate to which of the six classes the acquired sample belongs. Results show that the proposed method achieves its goal, since it correctly detects liveness in almost 100% of cases.