Detecting fingerprint distortion from a single image

Abstract

Elastic distortion of friction ridge skin is one of the major challenges in fingerprint matching. Since existing fingerprint matching systems cannot match seriously distorted fingerprints, criminals may purposely distort their fingerprints to evade identification. Existing distortion detection techniques require availability of specialized hardware or fingerprint video, limiting their use in real applications. In this paper we conduct a study on fingerprint distortion and develop an algorithm to detect fingerprint distortion from a single image which is captured using traditional fingerprint sensing techniques. The detector is based on analyzing ridge period and orientation information. Promising results are obtained on a public domain fingerprint database containing distorted fingerprints.