Please use this identifier to cite or link to this item:
Title: Unsupervised Fingerprint Classification with Directional Flow Filtering
Authors: Özbayoğlu, Ahmet Murat
Keywords: Fingerprint classification
fingerprint identification
neural networks
unsupervised learning
Issue Date: Nov-2019
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Özbayoğlu, A. M. (2019, November). Unsupervised Fingerprint Classification with Directional Flow Filtering. In 2019 1st International Informatics and Software Engineering Conference (UBMYK) (pp. 1-4). IEEE.
Abstract: In this study, an unsupervised neural network model is proposed for fingerprint classification. The proposed model uses directional flow or local ridge orientation (LRO) information and the relative locations of the fingerprint singular points as features for the neural network. The LRO is obtained by storing the directional data in a neighborhood from the raw fingerprint and this data is filtered to prevent the flow errors due to noisy sections of the scanned fingerprint. From the resulting LRO data, the singular points are extracted and the information is used as the input to the SimNet unsupervised neural network model and the fingerprint is classified accordingly. For identification, the raw image is passed through a band-pass filter and the minutiae are extracted from the processed and thinned fingerprint image. The fingerprint identification is performed within the obtained class by comparing the minutiae of the input fingerprint to the other existing prints in that class. The number of classes can be adjusted by the number of the singular points and the distance between these points. The results show that the model can generate a hierarchical classification model that can reduce the search space for identification which could be used in small to mid size fingerprint database applications. © 2019 IEEE.
ISBN: 978-172813992-0
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Show full item record

CORE Recommender


checked on Sep 23, 2022

Page view(s)

checked on Feb 6, 2023

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.