A Robust Document Identification Framework through f-BP Fingerprint
The identification of printed materials is a critical and challenging issue for security purposes, especially when it comes to documents such as banknotes, tickets, or rare collectable cards: eligible targets for ad hoc forgery. State-of-the-art methods require expensive and specific industrial equi...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Journal of Imaging |
Subjects: | |
Online Access: | https://www.mdpi.com/2313-433X/7/8/126 |
id |
doaj-cb3fec0398d345f9a61fee382de84c89 |
---|---|
record_format |
Article |
spelling |
doaj-cb3fec0398d345f9a61fee382de84c892021-08-26T13:56:27ZengMDPI AGJournal of Imaging2313-433X2021-07-01712612610.3390/jimaging7080126A Robust Document Identification Framework through f-BP FingerprintFrancesco Guarnera0Oliver Giudice1Dario Allegra2Filippo Stanco3Sebastiano Battiato4Salvatore Livatino5Vito Matranga6Angelo Salici7Department of Mathematics and Computer Science, University of Catania, 95125 Catania, ItalyDepartment of Mathematics and Computer Science, University of Catania, 95125 Catania, ItalyDepartment of Mathematics and Computer Science, University of Catania, 95125 Catania, ItalyDepartment of Mathematics and Computer Science, University of Catania, 95125 Catania, ItalyDepartment of Mathematics and Computer Science, University of Catania, 95125 Catania, ItalySchool of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UKRaggruppamento Carabinieri Investigazioni Scientifiche, RIS di Messina, 98122 Messina, ItalyRaggruppamento Carabinieri Investigazioni Scientifiche, RIS di Messina, 98122 Messina, ItalyThe identification of printed materials is a critical and challenging issue for security purposes, especially when it comes to documents such as banknotes, tickets, or rare collectable cards: eligible targets for ad hoc forgery. State-of-the-art methods require expensive and specific industrial equipment, while a low-cost, fast, and reliable solution for document identification is increasingly needed in many contexts. This paper presents a method to generate a robust fingerprint, by the extraction of translucent patterns from paper sheets, and exploiting the peculiarities of binary pattern descriptors. A final descriptor is generated by employing a block-based solution followed by principal component analysis (PCA), to reduce the overall data to be processed. To validate the robustness of the proposed method, a novel dataset was created and recognition tests were performed under both ideal and noisy conditions.https://www.mdpi.com/2313-433X/7/8/126document identificationbinary patterntexture fingerprint |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Francesco Guarnera Oliver Giudice Dario Allegra Filippo Stanco Sebastiano Battiato Salvatore Livatino Vito Matranga Angelo Salici |
spellingShingle |
Francesco Guarnera Oliver Giudice Dario Allegra Filippo Stanco Sebastiano Battiato Salvatore Livatino Vito Matranga Angelo Salici A Robust Document Identification Framework through f-BP Fingerprint Journal of Imaging document identification binary pattern texture fingerprint |
author_facet |
Francesco Guarnera Oliver Giudice Dario Allegra Filippo Stanco Sebastiano Battiato Salvatore Livatino Vito Matranga Angelo Salici |
author_sort |
Francesco Guarnera |
title |
A Robust Document Identification Framework through f-BP Fingerprint |
title_short |
A Robust Document Identification Framework through f-BP Fingerprint |
title_full |
A Robust Document Identification Framework through f-BP Fingerprint |
title_fullStr |
A Robust Document Identification Framework through f-BP Fingerprint |
title_full_unstemmed |
A Robust Document Identification Framework through f-BP Fingerprint |
title_sort |
robust document identification framework through f-bp fingerprint |
publisher |
MDPI AG |
series |
Journal of Imaging |
issn |
2313-433X |
publishDate |
2021-07-01 |
description |
The identification of printed materials is a critical and challenging issue for security purposes, especially when it comes to documents such as banknotes, tickets, or rare collectable cards: eligible targets for ad hoc forgery. State-of-the-art methods require expensive and specific industrial equipment, while a low-cost, fast, and reliable solution for document identification is increasingly needed in many contexts. This paper presents a method to generate a robust fingerprint, by the extraction of translucent patterns from paper sheets, and exploiting the peculiarities of binary pattern descriptors. A final descriptor is generated by employing a block-based solution followed by principal component analysis (PCA), to reduce the overall data to be processed. To validate the robustness of the proposed method, a novel dataset was created and recognition tests were performed under both ideal and noisy conditions. |
topic |
document identification binary pattern texture fingerprint |
url |
https://www.mdpi.com/2313-433X/7/8/126 |
work_keys_str_mv |
AT francescoguarnera arobustdocumentidentificationframeworkthroughfbpfingerprint AT olivergiudice arobustdocumentidentificationframeworkthroughfbpfingerprint AT darioallegra arobustdocumentidentificationframeworkthroughfbpfingerprint AT filippostanco arobustdocumentidentificationframeworkthroughfbpfingerprint AT sebastianobattiato arobustdocumentidentificationframeworkthroughfbpfingerprint AT salvatorelivatino arobustdocumentidentificationframeworkthroughfbpfingerprint AT vitomatranga arobustdocumentidentificationframeworkthroughfbpfingerprint AT angelosalici arobustdocumentidentificationframeworkthroughfbpfingerprint AT francescoguarnera robustdocumentidentificationframeworkthroughfbpfingerprint AT olivergiudice robustdocumentidentificationframeworkthroughfbpfingerprint AT darioallegra robustdocumentidentificationframeworkthroughfbpfingerprint AT filippostanco robustdocumentidentificationframeworkthroughfbpfingerprint AT sebastianobattiato robustdocumentidentificationframeworkthroughfbpfingerprint AT salvatorelivatino robustdocumentidentificationframeworkthroughfbpfingerprint AT vitomatranga robustdocumentidentificationframeworkthroughfbpfingerprint AT angelosalici robustdocumentidentificationframeworkthroughfbpfingerprint |
_version_ |
1721192280586452992 |