Segmentation of fingerprint images using the simplest neural networks

Samara University Repository

Welcome to the Samara University repository!

This is an open electronic archive created to preserve and disseminate the scientific results of our university. The works of researchers, faculty members, and students are available to everyone for academic and research purposes.

The repository contains dissertations, research articles, educational and methodological materials, monographs, and regulatory documents. The collections cover a wide range of fields: from aerospace technologies, engine engineering, and computer science to history, linguistics, mathematics, and ecology. The archive brings together the scientific heritage of the university, including materials prepared during the period of Samara State Aerospace University and Samara State University.

Looking for publications by author, title, date, or subject? Full-text search will provide relevant results. Want to explore the academic life more closely? Browse materials by the universityâs organizational units.

Descriptions of all publications and articles available in the repository can be found in the libraryâs electronic catalog. Staff and students can log in via the menu "Login -> My Resource Archive" using their personal account credentials (SSAU_id).

Use the archive for study, research, and professional development!

Full metadata record

DC Field	Value	Language
dc.date	2018
dc.date.accessioned	2025-08-22T12:19:37Z	-
dc.date.available	2025-08-22T12:19:37Z	-
dc.date.issued	2018
dc.identifier.identifier	Dspace\SGAU\20180514\69217
dc.identifier.citation	Pasynkov M.K. Segmentation of fingerprint images using the simplest neural networks / M.K. Pasynkov and M.Y. Khachay // Сборник трудов IV международной конференции и молодежной школы «Информационные технологии и нанотехнологии» (ИТНТ-2018) - Самара: Новая техника, 2018. - С.1267-1274
dc.identifier.uri	http://repo.ssau.ru/jspui/handle/123456789/13983	-
dc.description	Основная статья
dc.description.abstract	Segmentation of fingerprint images is one of the most important problems in automated fingerprint identification system (AFIS). Segmentation is used to separate the area of the fingerprint (foreground) from the background and areas that cannot be recovered. We propose a new algorithm for fingerprint segmentation based on simplest neural networks, binary region labeling technique, and morphological image processing. This approach was tested on public fingerprint dataset provided by Fingerprint Verification Competition (FVC) 2002. The experimental results showed an impressive accuracy was obtained: FAR 2.4%, FRR 1.1% with per-pixel comparison with the reference.
dc.language	en
dc.publisher	Новая техника
dc.title	Segmentation of fingerprint images using the simplest neural networks
dc.type	Article
local.identifier.olduri	http://repo.ssau.ru/handle/Informacionnye-tehnologii-i-nanotehnologii/Segmentation-of-fingerprint-images-using-the-simplest-neural-networks-69217
local.identifier.olduri	http://repo.ssau.ru/handle/Informacionnye-tehnologii-i-nanotehnologii/Segmentation-of-fingerprint-images-using-the-simplest-neural-networks-69217
Appears in Collections:	Информационные технологии и нанотехнологии

Files in This Item:

File	Description	Size	Format
paper_166.pdf	Основная статья	1.98 MB	Adobe PDF	View/Open

Show simple item record