Comparison of classification methods for perspiration-based liveness algorithm

In the modern world there is a need for security. Biometric technologies provide a means for providing this security. Of the many different available biometric technologies, fingerprint recognition is the most popular. As with all security measures, biometric devices may be subject to attacks on the system. Fingerprint scanners may be susceptible to spoofing using artificial materials, or in the worst case, dismembered fingers. Liveness, i.e. to determine whether the introduced biometric is coming from a live source, has been suggested as a means to circumvent attacks that use spoof fingers. It has been shown that water based casting materials and cadaver fingers were able to be scanned and verified for most fingerprint scanner technologies. In our laboratory an anti-spoofing method based on liveness detection has been developed for use in fingerprint scanners. This method quantifies a specific temporal perspiration pattern present in fingerprints acquired from live claimants. For this thesis, perspiration detection algorithm is optimized for different fingerprint scanner technologies, using a larger, more diverse data set, and a shorter time window. Several classification methods are tested in order to separate live and spoof fingerprint images. Each method had a different performance with respect to each scanner and time window. All the classifiers achieved approximately 90% classification rate for all scanners, using the reduced time window and the more comprehensive training and test sets. Based on the classification results, it is believed that this perspiration-based method has a potential to reduce the susceptibility of the fingerprint scanners to spoof attacks.

Name thesis:degree_name

MS

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Lane Department of Computer Science and Electrical Engineering

Year dc:date.available

2003

Author dc:creator

• Parthasaradhi, Sujan T. V.

Contributors dc:contributor

• Stephanie Schuckers.

• Electrical engineering

Identifier

https://researchrepository.wvu.edu/etd/1394

OAI identifier oai:identifier

oai:researchrepository.wvu.edu:etd-2397