TY - JOUR
T1 - Digital Forensic Analysis for Source Video Identification
T2 - a Survey
AU - Akbari, Younes
AU - Almaadeed, Somaya
AU - Elharrouss, Omar
AU - Khelifi, Fouad
AU - Lawgaly, Ashref
AU - Bouridane, Ahmed
N1 - Funding information: This publication was made possible by NPRP grant # NPRP12S-0312-190332 from Qatar National Research Fund (a member of Qatar Foundation). The statement made herein are solely the responsibility of the authors.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - In recent years, many digital devices have been equipped with a video camera that allows videos to be recorded in good quality, free of charge and without restrictions. Concurrently, the widespread use of digital videos via web-based multimedia systems and mobile smartphone applications such as YouTube, Facebook, Twitter and WhatsApp is becoming increasing important. However, security challenges have emerged and are spreading worldwide. These issues may lead to serious problems, particularly in situations where video is a key part of decision-making in crimes, including movie piracy and child pornography. Thus, to increase the trustworthiness of using digital video in daily life, copyright protection and video authentication must be used. Although source camera identification based on digital images has attracted many researchers’ attention, less research has been performed on the forensic analysis of videos due to certain challenges, such as compression, stabilization, scaling, and cropping, as well as differences between frame types that can occur when a video is stored in digital devices. Thus, there are insufficient large standard digital video databases and updated databases with new devices based on new technologies. The goal of this paper is to offer an inclusive overview of what has been done over the last decade in the field of source video identification by examining existing techniques, such as photo response nonuniformity (PRNU) and machine learning approaches, and describing some popular video databases.
AB - In recent years, many digital devices have been equipped with a video camera that allows videos to be recorded in good quality, free of charge and without restrictions. Concurrently, the widespread use of digital videos via web-based multimedia systems and mobile smartphone applications such as YouTube, Facebook, Twitter and WhatsApp is becoming increasing important. However, security challenges have emerged and are spreading worldwide. These issues may lead to serious problems, particularly in situations where video is a key part of decision-making in crimes, including movie piracy and child pornography. Thus, to increase the trustworthiness of using digital video in daily life, copyright protection and video authentication must be used. Although source camera identification based on digital images has attracted many researchers’ attention, less research has been performed on the forensic analysis of videos due to certain challenges, such as compression, stabilization, scaling, and cropping, as well as differences between frame types that can occur when a video is stored in digital devices. Thus, there are insufficient large standard digital video databases and updated databases with new devices based on new technologies. The goal of this paper is to offer an inclusive overview of what has been done over the last decade in the field of source video identification by examining existing techniques, such as photo response nonuniformity (PRNU) and machine learning approaches, and describing some popular video databases.
KW - Survey
KW - Source camera identification
KW - Video
KW - PRNU
KW - Machine learning methods
UR - http://www.scopus.com/inward/record.url?scp=85129967683&partnerID=8YFLogxK
U2 - 10.1016/j.fsidi.2022.301390
DO - 10.1016/j.fsidi.2022.301390
M3 - Review article
SN - 0379-0738
VL - 41
SP - 1
EP - 13
JO - Forensic Science International
JF - Forensic Science International
M1 - 301390
ER -
