Liveness Detection for Fingerprint Scanners Based on the Statistics of Wavelet Signal Processing

Abstract

Fingerprint scanners can be spoofed by artificial fingers using moldable plastic, clay, Play-Doh, gelatin, silicone rubber materials, etc. Liveness detection is an anti-spoofing method which can detect physiological signs of life from fingerprints to ensure only live fingers can be captured for enrollment or authentication. In this paper, a new method based on the wavelet transform on the ridge signal extracted along the ridge mask is proposed which can detect the perspiration phenomenon using only a single image. Statistical features are extracted for multiresolution scales to discriminate between live and non-live fingers. Based on these features, we use a classification tree to generate the decision rules for the liveness classification. We test this method on the dataset which contains about 58 live, 80 spoof (50 made from Play-Doh and 30 made from gelatin), and 25 cadaver subjects for 3 different scanners. Also, we test this method on a second dataset which contains 33 live and 33 spoof (made from gelatin) subjects. The proposed liveness detection method is purely software based and application of this method can provide anti-spoofing protection for fingerprint scanners.