Deep Learning for Detection of Object-Based Forgery in Advanced Video

Yao, Ye; Shi, Yun-Qing; Weng, Shaowei; Guan, Bo

doi:10.3390/sym10010003

Cited by 61 publications

(40 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to hardware memory limitations, we needed to clip these full-size images into smaller image patches before they were fed into our neural network for training. This is also a data augmentation strategy in deep learning approaches to computer vision [8]. Data augmentation [22] helps to increase the amount of training samples used for deep learning training and improve the generalization capability of the trained model.…”

Section: The Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Distinguishing Computer-Generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning

Yao

Zhang

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

Computer-generated graphics (CGs) are images generated by computer software. The rapid development of computer graphics technologies has made it easier to generate photorealistic computer graphics, and these graphics are quite difficult to distinguish from natural images (NIs) with the naked eye. In this paper, we propose a method based on sensor pattern noise (SPN) and deep learning to distinguish CGs from NIs. Before being fed into our convolutional neural network (CNN)-based model, these images—CGs and NIs—are clipped into image patches. Furthermore, three high-pass filters (HPFs) are used to remove low-frequency signals, which represent the image content. These filters are also used to reveal the residual signal as well as SPN introduced by the digital camera device. Different from the traditional methods of distinguishing CGs from NIs, the proposed method utilizes a five-layer CNN to classify the input image patches. Based on the classification results of the image patches, we deploy a majority vote scheme to obtain the classification results for the full-size images. The experiments have demonstrated that (1) the proposed method with three HPFs can achieve better results than that with only one HPF or no HPF and that (2) the proposed method with three HPFs achieves 100% accuracy, although the NIs undergo a JPEG compression with a quality factor of 75.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

“…This predefined HPF was proposed as an image residual extraction model of a SQUARE 5 × 5 filter in [23]. Furthermore, this image residual extraction model has been applied to deep-learning-based camera model identification [11] as well as to deep-learning-based video forgery detection [8] and has obtained perfect performance.…”

Section: The Proposed Methodsmentioning

confidence: 99%

Distinguishing Computer-Generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning

Yao

Zhang

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, the introduction of deep learning approaches has led to improved performance and promising results for video manipulation detection. In [22], the inter-frame differences are calculated for the entire video, then a high-pass filter is applied to each difference output and the outputs are used to classify the entire video as tampered or untampered. High-pass filters have been used successfully in the past in conjunction with machine learning approaches with promising results in images [4].…”

Section: Related Workmentioning

confidence: 99%

Detecting Tampered Videos with Multimedia Forensics and Deep Learning

Zampoglou

Markatopoulou

Mercier³

et al. 2018

MultiMedia Modeling

View full text Add to dashboard Cite

User-Generated Content (UGC) has become an integral part of the news reporting cycle. As a result, the need to verify videos collected from social media and Web sources is becoming increasingly important for news organisations. While video verification is attracting a lot of attention, there has been limited effort so far in applying video forensics to real-world data. In this work we present an approach for automatic video manipulation detection inspired by manual verification approaches. In a typical manual verification setting, video filter outputs are visually interpreted by human experts. We use two such forensics filters designed for manual verification, one based on Discrete Cosine Transform (DCT) coefficients and a second based on video requantization errors, and combine them with Deep Convolutional Neural Networks (CNN) designed for image classification. We compare the performance of the proposed approach to other works from the state of the art, and discover that, while competing approaches perform better when trained with videos from the same dataset, one of the proposed filters demonstrates superior performance in cross-dataset settings. We discuss the implications of our work and the limitations of the current experimental setup, and propose directions for future research in this area.

show abstract

“…This task becomes more challenging when the key frames extraction needs to guarantee information integrity with fewer key frames (Xia et al, 2017). The selection of suitable key frames are essential and crucial for various fields such as a compact representation in video summarization, searching and retrieval (Mizher et al, 2017b), preserving sufficient information about objects or events effectively in object-based video forgery detection system (Yao et al, 2017;Mizher et al, 2017b). Therefore, a new key frames extraction algorithm that is able to detect object motion sparsity and to extract the sufficient event key frames from complex video shots, is desirable and essential.…”

Section: Introductionmentioning

confidence: 99%

An Improved Action Key Frames Extraction Algorithm for Complex Colour Video Shot Summarization

Mizher

Choo

Abdullah

et al. 2019

JICT

View full text Add to dashboard Cite

Key frame extraction is one of the critical techniques in computer vision fields such as video search, video identification and video forgeries detection. The extracted key frames should be sufficient key frames that preserve main actions in a video with compact representation. The objective of this work is to improve our previous action key frames extraction algorithm (AKF) by adapting a threshold which selects action key frames as final key frames. The threshold adaptation was achieved by using the mean value, the standard deviation, and the L1norm instead of the comparison of user summaries evaluation method to obtain a fully automatic video summarisation algorithm, and by eliminating the conditions in selecting the final key frames to reduce the complexity of the algorithm. We have validated our proposed Improved AKF on complex colour video shots instead of the simple grey level video shots.144 frames, reduce processing complexity, and preserve sufficient information about the main actions in a video shot. We then evaluated the Improved AKF algorithm with the-state-of-theart algorithms in terms of compression ratio using Paul videos and Shih-Tang dataset. The evaluation results showed that the Improved AKF algorithm achieved better compression ratio and retained sufficient information in the extracted action key frames under different testing video shots. Therefore, the improved AKF algorithm is a suitable technique for applications in computer vision fields such as passive object-based video authentication systems.

show abstract

Deep Learning for Detection of Object-Based Forgery in Advanced Video

Cited by 61 publications

References 31 publications

Distinguishing Computer-Generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning

Distinguishing Computer-Generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning

Detecting Tampered Videos with Multimedia Forensics and Deep Learning

An Improved Action Key Frames Extraction Algorithm for Complex Colour Video Shot Summarization

Contact Info

Product

Resources

About