Fingerprint matching, spoof and liveness detection: classification and literature review
- PDF / 1,183,901 Bytes
- 18 Pages / 612.284 x 802.205 pts Page_size
- 107 Downloads / 224 Views
Fingerprint matching, spoof and liveness detection: classification and literature review Syed Farooq ALI 2
1
, Muhammad Aamir KHAN2, Ahmed Sohail ASLAM3
1 Department of Software Engineering, University of Management and Technology, Lahore 54770, Pakistan Department of Informatics and Systems, University of Management and Technology, Lahore 54770, Pakistan 3 Department of Computer Science, University of Management and Technology, Lahore 54770, Pakistan
c Higher Education Press 2020
Abstract Fingerprint matching, spoof mitigation and liveness detection are the trendiest biometric techniques, mostly because of their stability through life, uniqueness and their least risk of invasion. In recent decade, several techniques are presented to address these challenges over well-known data-sets. This study provides a comprehensive review on the fingerprint algorithms and techniques which have been published in the last few decades. It divides the research on fingerprint into nine different approaches including feature based, fuzzy logic, holistic, image enhancement, latent, conventional machine learning, deep learning, template matching and miscellaneous techniques. Among these, deep learning approach has outperformed other approaches and gained significant attention for future research. By reviewing fingerprint literature, it is historically divided into four eras based on 106 referred papers and their cumulative citations. Keywords computer society, template matching, fingerprint recognition, survey, deep learning, machine learning
1
Introduction
Every human has patterns of raised and shallow ridges on the finger tips which give rise to fingerprints [1]. These ridges, also known as friction ridges, when collected as an image are called fingerprints. The ridge lines also have unique sub-patterns or features, for example number of ridges and their groupings, called minutiae as well [2]. A standard set of these fingerprints should contain the images of all fingers. Classically, these fingerprints were captured by inking the finger ends and pressing them on paper, providing inked marks of lines corresponding to the raised ridges for each finger [3]. The un-inked or empty regions along these lines also seemed to run in the form of white lines corresponding to the shallow grooves or valleys. The modern method to acquire fingerprints is to take the picture of these patterns through an imaging device. The overall pattern of these lines in a fingerprint was found to be unique for an individual and in 1893 the Home Ministry Office, UK accepted that no two individuals have the same fingerprints [4]. Received July 1, 2019; accepted March 5, 2020 E-mail: [email protected]
Fingerprints are the oldest and most thoroughly explored and widely used biometric traits in reliable human recognition or identification applications [5]. The process of identifying the humans based on fingerprints, known as dactyloscopy, has been in use for decades [6]. Fingerprints, which are one of the most enduring forms of biological traits, are incr
Data Loading...
