A high performance fingerprint liveness detection method based on quality related features

Abstract

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution and sharing with colleagues.Other uses, including reproduction and distribution, or selling or licensing copies, or posting to personal, institutional or third party websites are prohibited. a b s t r a c tA new software-based liveness detection approach using a novel fingerprint parameterization based on quality related features is proposed. The system is tested on a highly challenging database comprising over 10,500 real and fake images acquired with five sensors of different technologies and covering a wide range of direct attack scenarios in terms of materials and procedures followed to generate the gummy fingers. The proposed solution proves to be robust to the multi-scenario dataset, and presents an overall rate of 90% correctly classified samples. Furthermore, the liveness detection method presented has the added advantage over previously studied techniques of needing just one image from a finger to decide whether it is real or fake. This last characteristic provides the method with very valuable features as it makes it less intrusive, more user friendly, faster and reduces its implementation costs.

Image Quality Measures for Gender Classification

“…gait, signature, voice) to fraudulently access the biometric system. [1] Various researches have now been focused to detect the fake samples and reject them, thus increasing the efficiency and reliability of systems [2]. The most important thing to be noticed at the time of identification is to know whether the person to be identified is actually present at the time of acquisition.…”

Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns

“…or physical devices (key, card, etc.) [1]. However, providing to the sensor a fake physical biometric can be an easy way to overtake the system's security.…”

“…The features used to distinguish between real and fake fingers are extracted from the image of the fingerprint. There are techniques such as in [1] and [10], in which the features used in the classifier are based on the specific fingerprint measurements, such as ridge strength, continuity and clarity. In contrast, some works use general feature extractors, such as Weber Local Descriptor (WLD) [11], which is a texture descriptor composed of differential excitation and orientation components.A local descriptor that uses local amplitude contrast (spatial domain) and phase (frequency domain) to form a bi-dimensional contrast-phase histogram was proposed in [12].…”

Exploting periocular and RGB information in fake iris detection

“…There has been also research concerned with the synthesis of artificial images [9], accompanied by the release of datasets of synthetic iris images, such as the WVU-Synthetic Iris DB 2 [2]. The latter followed a previous framework that we initiated with the use of trait-specific quality properties for liveness detection, including fingerprints [10], [11] and iris [12]. For the case of iris samples, the experiments reported in [2] achieved a classification rate of over 97% using the ATVSFlr DB, and nearly 90% using synthetic iris images from the WVU-Synthetic Iris DB.…”