Face verification and recognition for digital forensics and information security

Giuseppe Amato; Fabrizio Falchi; Claudio Gennaro; Fabio Valerio Massoli; Nikolaos Passalis; Anastasios Tefas; Alessandro Trivilini; Claudio Vairo

doi:10.1109/ISDFS.2019.8757511

Face verification and recognition for digital forensics and information security

Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro, Fabio Valerio Massoli, Nikolaos Passalis, Anastasios Tefas, Alessandro Trivilini, Claudio Vairo

Computing Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

24 Citations (Scopus)

Abstract

In this paper, we present an extensive evaluation of face recognition and verification approaches performed by the European COST Action MULTI-modal Imaging of FOREnsic SciEnce Evidence (MULTI-FORESEE). The aim of the study is to evaluate various face recognition and verification methods, ranging from methods based on facial landmarks to state-of-the-art off-the-shelf pre-trained Convolutional Neural Networks (CNN), as well as CNN models directly trained for the task at hand. To fulfill this objective, we carefully designed and implemented a realistic data acquisition process, that corresponds to a typical face verification setup, and collected a challenging dataset to evaluate the real world performance of the aforementioned methods. Apart from verifying the effectiveness of deep learning approaches in a specific scenario, several important limitations are identified and discussed through the paper, providing valuable insight for future research directions in the field.

Original language	English
Title of host publication	7th International Symposium on Digital Forensics and Security, ISDFS 2019
Editors	Asaf Varol, Murat Karabatak, Cihan Varol, Sevginur Teke
Publisher	IEEE
ISBN (Electronic)	9781728128276
DOIs	https://doi.org/10.1109/ISDFS.2019.8757511
Publication status	Published - 1 Jun 2019
Publication type	A4 Article in conference proceedings
Event	International Symposium on Digital Forensics and Security - Barcelos, Portugal Duration: 10 Jun 2019 → 12 Jun 2019

Conference

Conference	International Symposium on Digital Forensics and Security
Country/Territory	Portugal
City	Barcelos
Period	10/06/19 → 12/06/19

Keywords

Deep learning
Face verification
Forensics
Security
Surveillance

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Health Informatics
Pathology and Forensic Medicine
Computer Networks and Communications
Computer Science Applications
Safety, Risk, Reliability and Quality

Access to Document

10.1109/ISDFS.2019.8757511

Cite this

Amato, G., Falchi, F., Gennaro, C., Massoli, F. V., Passalis, N., Tefas, A., Trivilini, A., & Vairo, C. (2019). Face verification and recognition for digital forensics and information security. In A. Varol, M. Karabatak, C. Varol, & S. Teke (Eds.), 7th International Symposium on Digital Forensics and Security, ISDFS 2019 IEEE. https://doi.org/10.1109/ISDFS.2019.8757511

@inproceedings{2f6e3fa58c7b4de78502c040d30a61c9,

title = "Face verification and recognition for digital forensics and information security",

abstract = "In this paper, we present an extensive evaluation of face recognition and verification approaches performed by the European COST Action MULTI-modal Imaging of FOREnsic SciEnce Evidence (MULTI-FORESEE). The aim of the study is to evaluate various face recognition and verification methods, ranging from methods based on facial landmarks to state-of-the-art off-the-shelf pre-trained Convolutional Neural Networks (CNN), as well as CNN models directly trained for the task at hand. To fulfill this objective, we carefully designed and implemented a realistic data acquisition process, that corresponds to a typical face verification setup, and collected a challenging dataset to evaluate the real world performance of the aforementioned methods. Apart from verifying the effectiveness of deep learning approaches in a specific scenario, several important limitations are identified and discussed through the paper, providing valuable insight for future research directions in the field.",

keywords = "Deep learning, Face verification, Forensics, Security, Surveillance",

author = "Giuseppe Amato and Fabrizio Falchi and Claudio Gennaro and Massoli, {Fabio Valerio} and Nikolaos Passalis and Anastasios Tefas and Alessandro Trivilini and Claudio Vairo",

note = "EXT={"}Tefas, Anastasios{"}; International Symposium on Digital Forensics and Security ; Conference date: 10-06-2019 Through 12-06-2019",

year = "2019",

month = jun,

day = "1",

doi = "10.1109/ISDFS.2019.8757511",

language = "English",

editor = "Asaf Varol and Murat Karabatak and Cihan Varol and Sevginur Teke",

booktitle = "7th International Symposium on Digital Forensics and Security, ISDFS 2019",

publisher = "IEEE",

address = "United States",

}

Amato, G, Falchi, F, Gennaro, C, Massoli, FV, Passalis, N, Tefas, A, Trivilini, A & Vairo, C 2019, Face verification and recognition for digital forensics and information security. in A Varol, M Karabatak, C Varol & S Teke (eds), 7th International Symposium on Digital Forensics and Security, ISDFS 2019. IEEE, International Symposium on Digital Forensics and Security, Barcelos, Portugal, 10/06/19. https://doi.org/10.1109/ISDFS.2019.8757511

Face verification and recognition for digital forensics and information security. / Amato, Giuseppe; Falchi, Fabrizio; Gennaro, Claudio et al.
7th International Symposium on Digital Forensics and Security, ISDFS 2019. ed. / Asaf Varol; Murat Karabatak; Cihan Varol; Sevginur Teke. IEEE, 2019.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Face verification and recognition for digital forensics and information security

AU - Amato, Giuseppe

AU - Falchi, Fabrizio

AU - Gennaro, Claudio

AU - Massoli, Fabio Valerio

AU - Passalis, Nikolaos

AU - Tefas, Anastasios

AU - Trivilini, Alessandro

AU - Vairo, Claudio

N1 - EXT="Tefas, Anastasios"

PY - 2019/6/1

Y1 - 2019/6/1

N2 - In this paper, we present an extensive evaluation of face recognition and verification approaches performed by the European COST Action MULTI-modal Imaging of FOREnsic SciEnce Evidence (MULTI-FORESEE). The aim of the study is to evaluate various face recognition and verification methods, ranging from methods based on facial landmarks to state-of-the-art off-the-shelf pre-trained Convolutional Neural Networks (CNN), as well as CNN models directly trained for the task at hand. To fulfill this objective, we carefully designed and implemented a realistic data acquisition process, that corresponds to a typical face verification setup, and collected a challenging dataset to evaluate the real world performance of the aforementioned methods. Apart from verifying the effectiveness of deep learning approaches in a specific scenario, several important limitations are identified and discussed through the paper, providing valuable insight for future research directions in the field.

AB - In this paper, we present an extensive evaluation of face recognition and verification approaches performed by the European COST Action MULTI-modal Imaging of FOREnsic SciEnce Evidence (MULTI-FORESEE). The aim of the study is to evaluate various face recognition and verification methods, ranging from methods based on facial landmarks to state-of-the-art off-the-shelf pre-trained Convolutional Neural Networks (CNN), as well as CNN models directly trained for the task at hand. To fulfill this objective, we carefully designed and implemented a realistic data acquisition process, that corresponds to a typical face verification setup, and collected a challenging dataset to evaluate the real world performance of the aforementioned methods. Apart from verifying the effectiveness of deep learning approaches in a specific scenario, several important limitations are identified and discussed through the paper, providing valuable insight for future research directions in the field.

KW - Deep learning

KW - Face verification

KW - Forensics

KW - Security

KW - Surveillance

U2 - 10.1109/ISDFS.2019.8757511

DO - 10.1109/ISDFS.2019.8757511

M3 - Conference contribution

BT - 7th International Symposium on Digital Forensics and Security, ISDFS 2019

A2 - Varol, Asaf

A2 - Karabatak, Murat

A2 - Varol, Cihan

A2 - Teke, Sevginur

PB - IEEE

T2 - International Symposium on Digital Forensics and Security

Y2 - 10 June 2019 through 12 June 2019

ER -

Face verification and recognition for digital forensics and information security

Abstract

Conference

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this