A detailed analysis of image and video forgery detection techniques

Yadav, Divakar

doi:10.1007/s00371-021-02347-4

Cited by 33 publications

(12 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Video forensics is a key aspect in the field of digital forensics, especially in domains of criminal justice and security surveillance. Existing video forensics methods mainly include: (1) Frame-level analysis [33,39]: detecting possible editing or tampering by analyzing each frame of the video. (2) Metadata analysis [2,23]: metadata contained in the video file, such as shooting time and equipment information, can be used to verify the authenticity of the video.…”

Section: Related Workmentioning

confidence: 99%

Contour-Assistance-Based Video Matting Localization

zhu,

Ding,

Zhao

et al. 2024

Preprint

View full text Add to dashboard Cite

Video matting is developed to replace the foreground object in video frames by forecasting their alpha matte, which was originally used in film special effects production, advertisement production, and live streaming. However , it can be used as a malicious tampering operation, and hence its passive forensics is especially important as the key foundation of judicial forensics. A key challenge in the current detection of video matting tampering is how to locate the complete tampered region without generating false alarms, not only that tampering detection of video needs to take into account the temporal dimension, but successive frames need to be analyzed to detect forged video regions. In this paper, a dual-branch network is constructed by integrating the object contour information to capture rich tampering traces and contour features, which are introduced by focusing on the information of the entire video sequence. In addition, a manipulation contour detection module and a feature enhancement module are integrated to identify tampering regions better. Extensive experimental results on publicly manipulated and synthetic manipulated datasets show that the proposed method can accurately locate tampered regions and outperform state-of-the-art video matting forensic methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Contour-Assistance-Based Video Matting Localization

zhu,

Ding,

Zhao

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…DL has dominated research in various fields over the past decade [53], [54]. In the last five years, DL-based methods have surpassed traditional physics-based methods for solving IFD problems [42], [43], [44], [55], [56]. The general DL-based image forgery detection pipeline is illustrated in Figure 3 where the entire input image or divided patches are fed into a deep neural network (DNN) for feature extraction.…”

Section: Overview Of Deep Neural Network Architecturesmentioning

confidence: 99%

Toward Deep-Learning-Based Methods in Image Forgery Detection: A Survey

Pham

Park

2023

IEEE Access

View full text Add to dashboard Cite

In the last decades, deep learning (DL) has emerged as a powerful and dominant technique for solving challenging problems in various fields. Likewise, in the field of digital image forensics, a large and growing body of literature investigates DL-based techniques for detecting and classifying tampered regions in images. This article aims to provides a comprehensive survey of state-of-the-art DL-based methods for image-forgery detection. Copy-move images and spliced images, two of the most popular types of forged images, were considered. Recently, owing to advances in DL, DL-based approaches have yielded much better results as compared to traditional non-DL-based ones. The surveyed techniques were proposed by developing or fusing various efficient DL methods, such as CNN, RCNN, or LSTM to adapt to detecting tampered traces. INDEX TERMSCopy-move image, image forgery, spliced image.

show abstract

“…Fake photos and videos are one form of cyberbullying. In this virtual environment, people may easily manipulate and exploit media to harass and shame others (Tyagi & Yadav, 2022). A metaverse user may construct a deep fake video of another person behaving inappropriately or saying things they would never utter.…”

Section: Creating Fake or Doctored Images Or Videosmentioning

confidence: 99%

Cyberbullying in the Metaverse

Upadhyay

Kumar

Sharma

et al. 2023

Journal of Global Information Management

View full text Add to dashboard Cite

The emergence of the metaverse, a virtual reality space, has ushered in a new era of digital experiences and interactions in global information systems. With its unique social norms and behaviors, this new world presents exciting opportunities for users to connect, socialize, and explore. However, as people spend more time in the metaverse, it has become increasingly apparent that the issue of cyberbullying needs to be addressed. Cyberbullying is a serious problem that can harm victims psychologically and physically. It involves using technology to harass, intimidate, or humiliate individuals or groups in global information systems. The risk of cyberbullying is high in the metaverse, where users are often anonymous. Therefore, it is crucial to establish a safer and more respectful culture within the metaverse to detect and prevent such incidents from happening.

show abstract

A detailed analysis of image and video forgery detection techniques

Cited by 33 publications

References 85 publications

Contour-Assistance-Based Video Matting Localization

Contour-Assistance-Based Video Matting Localization

Toward Deep-Learning-Based Methods in Image Forgery Detection: A Survey

Cyberbullying in the Metaverse

Contact Info

Product

Resources

About