Frame Identification of Object-Based Video Tampering Using Symmetrically Overlapped Motion Residual

Kim, Tae Hyung; Park, Cheol Woo; Eom, Il Kyu

doi:10.3390/sym14020364

Cited by 3 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Te reliance on motion residual-based analysis is not efective in detecting tampering techniques which does not signifcantly alter the motion patterns [6]. Existing face forgery detection methods based on frequency domain only focus on single frames and overlook the discriminative part and temporal frequency clues among diferent frames in synthesized videos [7].…”

Section: Discussion Of Challengesmentioning

confidence: 99%

“…Object-Based Forgery Detection. Kim et al [6] proposed a brand-new object-based frame identifcation network. Teir suggested technique leveraged symmetrically overlapping motion residuals to improve the ability to distinguish between video frames.…”

Section: Frame-based Forgery Detection Munawar and Noreenmentioning

confidence: 99%

“…With the advancement of multimedia editing capabilities in recent years, image and video alteration has become increasingly popular [6]. Current face forgery detection techniques based on frequency domain discover that, in contrast to authentic photographs, the generative adversarial network (GAN) fabricated images exhibit glaringly visible grid-like visual abnormalities in the frequency spectrum [7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Forged Video Detection Using Deep Learning: A SLR

Munawar,

Noreen,

Alharthi

et al. 2023

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

In today’s digital landscape, video and image data have emerged as pivotal and widely adopted means of communication. They serve not only as a ubiquitous mode of conveying information but also as indispensable evidential and substantiating elements across diverse domains, encompassing law enforcement, forensic investigations, media, and numerous others. This study employs a systematic literature review (SLR) methodology to meticulously investigate the existing body of knowledge. An exhaustive review and analysis of precisely 90 primary research studies were conducted, unveiling a range of research methodologies instrumental in detecting forged videos. The study’s findings shed light on several research methodologies integral to the detection of forged videos, including deep neural networks, convolutional neural networks, Deepfake analysis, watermarking networks, and clustering, amongst others. This array of techniques highlights the field and emphasizes the need to combat the evolving challenges posed by forged video content. The study shows that videos are susceptible to an array of manipulations, with key issues including frame insertion, deletion, and duplication due to their dynamic nature. The main limitations of the domain are copy-move forgery, object-based forgery, and frame-based forgery. This study serves as a comprehensive repository of the latest advancements and techniques, structured, and summarized to benefit researchers and practitioners in the field. It elucidates the complex challenges inherent to video forensics.

show abstract

Section: Discussion Of Challengesmentioning

confidence: 99%

Section: Frame-based Forgery Detection Munawar and Noreenmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forged Video Detection Using Deep Learning: A SLR

Munawar,

Noreen,

Alharthi

et al. 2023

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

show abstract

“…Consequently, it is also referred to as the Passive-Blind Technique [14]. Passive methods (i.e., represented in Figure 6 include the following sorts of altering parts based on the video's regional properties: 1) Spatial Tampering 2) Temporal Tampering 3) Spatio-Temporal Tampering 4) Re-Projection 3.2.1 Spatial Tampering/ Intra-frame Forgery Spatial Tampering or Intra-frame forgery determines the kind of counterfeit that involves manipulating the original contents of speci c frames [15]. It can be accomplished by modifying the pixel bits in a frame or the adjacent ones in a video sequence (i.e., along the x-y axis) [16].…”

Section: Passive Approachesmentioning

confidence: 99%

Video Forgery Detection for Surveillance Cameras: A Review

Tayfor,

Rashid,

Qader

et al. 2023

Preprint

View full text Add to dashboard Cite

Although video recording is now a standard feature in smartphones and other digital devices, digital records are affordable and straightforward to take and distribute on social media. Furthermore, digital recordings have recently become an essential part of our daily lives, ranging from personal experiences to surveillance footage that may now be utilised as evidence of proof. Thus, it is essential to create detection algorithms for this kind of captured video because the number of high-standard counterfeit videos on social networks and other media is increasing exponentially. Evaluating the integrity of surveillance videos is crucial with the advanced equipment of surveillance systems. As a result, the rapid increase in surveillance cameras has made progress in physical security, including in building homes, stores, governmental buildings, agencies, etc. Moreover, surveillance videos have lately been extensively used as significant evidence in the courts. The evidence from the video can be crucial for a court of justice and investigators to comprehend the incidents as they happened. Unfortunately, due to the widespread of video editing programs, the video forgery/ tampering process has become incredibly simple. Consequently, the courts refuse to accept these videos as evidence because there is some margin of doubt about their authenticity and integrity. Therefore, to avoid such a situation in the future, more efforts are needed in video forensics. For this reason, this paper reviews primarily all the techniques and methods proposed so far to find out forgery in surveillance recordings and how the authenticity of such videos is proven.

show abstract

Remote medical video region tamper detection system based on Wireless Sensor Network

Huang

2022

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

INTRODUCTION: A new telemedicine video tamper detection system based on wireless sensor network is proposed and designed in this paper. OBJECTIVES: This work is proposed to improve the performance of telemedicine video communication and accurately detect the tamper area in telemedicine video. METHODS: The sensor nodes in the sensing layer are responsible for collecting telemedicine video information and transmitting the information to the data layer. The data layer completes the storage of information and transmits it to the processing layer. The detection module of the processing layer detects the tampered area of the telemedicine video through two parts: suspicious moving point calculation and tamper detection, and transmits the detection results to the application display layer for display. RESULTS: The experimental results show that the designed detection system can accurately detect the tampered area in the telemedicine video, and the packet loss rate is significantly reduced, and the maximum packet loss rate is no more than 1%. CONCLUSION: The proposed detection system for remote medical video based on wireless sensor network can better meet the requirements of region tamper detection.

show abstract

Frame Identification of Object-Based Video Tampering Using Symmetrically Overlapped Motion Residual

Cited by 3 publications

References 33 publications

Forged Video Detection Using Deep Learning: A SLR

Forged Video Detection Using Deep Learning: A SLR

Video Forgery Detection for Surveillance Cameras: A Review

Remote medical video region tamper detection system based on Wireless Sensor Network

Contact Info

Product

Resources

About