Dense moment feature index and best match algorithms for video copy-move forgery detection

Zhong, Junliu; Pun, Chi‐Man; Gan, Yanfen

doi:10.1016/j.ins.2020.05.134

Cited by 28 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In video forensics, the problems related to computational cost and detection accuracy are of significant concern to the development of the strategies, as even a video of short length may run into thousands of frames. In addition, most previous approaches could not attain better computational efficiency and detection accuracy, not even revealing finding the forged areas with mirroring, as stated in References 8‐11.…”

Section: Introductionmentioning

confidence: 94%

Raven finch optimized deep convolutional neural network model for intra‐frame video forgery detection

Singla

Singh

Nagpal

2022

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARY Due to the tremendous growth of video editing software, it has become extremely simple to introduce malicious content by manipulating multimedia data. This may include modification of videos either by adding or deleting selective frames with malicious intentions. Hence, it is essential to find the forged frames of the videos by introducing efficient and reliable video forensic methods. This article presents an automatic intra‐frame video forgery detection strategy based on a hybrid optimization tuned deep‐convolutional neural network (deep‐CNN) classifier. The significance of the proposed method lies in developing the proposed raven‐finch optimization algorithm that tunes the weights of the deep‐CNN to exhibit enhanced detection accuracy. The proposed raven‐finch optimization algorithm combines raven search agents and finches search agents, possessing the benefits of both search agents. The features of the input video frames act as the input to the deep‐CNN classifier that detects forgery. The performance of the proposed raven‐finch‐based deep CNN method is analyzed in terms of the performance indices, such as accuracy, sensitivity, and specificity. It is attained to be 97.56%, 95.48%, and 96.38%, respectively, which shows the superiority of the proposed method for intra‐frame forgery detection.

show abstract

Section: Introductionmentioning

confidence: 94%

Raven finch optimized deep convolutional neural network model for intra‐frame video forgery detection

Singla

Singh

Nagpal

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…In the enhanced GWO technique, multi-objective functions like leader selection strategy and Pareto archive are applied to select the best solutions, and to eliminate the crowded segments. In the GWO technique, the encircling process is mathematically indicated in the next equations: (7) dis = |𝑐 × 𝑧 𝑢(𝑡) − 𝑧(𝑡)|, (8) 𝑧(𝑡 + 1) = 𝑧 𝑢(𝑡) − 𝑘 × dis, where dis represents distance, t states present iteration, 𝑧 𝑢(𝑡) indicates location of prey, 𝑧(𝑡) states position of grey wolf, 𝑘 and 𝑐 indicates coefficients. The coefficients 𝑘 = 2𝑜𝑟 1 − 𝑜 and 𝑐 = 2𝑟 2 , where 𝑜 is a decreasing parameter, 𝑟 1 and 𝑟 2 are random values that range between zero to one.…”

Section: Patch Segmentationmentioning

confidence: 99%

“…Numerous authentication techniques are introduced to secure the image communication process, where the authentication techniques are categorized into two types: active and passive authentication. Active authentication includes the techniques like cryptography, watermarking, etc., and inactive authentication, the original image content is available and compared with the test image, where the original image content is unavailable in passive authentication [7]. The test image is investigated without prior knowledge of the original image content, where this type of authentication is applied in forgery detection [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Copy-Move Forgery Detection Using Superpixel Clustering Algorithm and Enhanced GWO Based AlexNet Model

Tinnathi

Sudhavani²

2022

Cybernetics and Information Technologies

View full text Add to dashboard Cite

In this work a model is introduced to improve forgery detection on the basis of superpixel clustering algorithm and enhanced Grey Wolf Optimizer (GWO) based AlexNet. After collecting the images from MICC-F600, MICC-F2000 and GRIP datasets, patch segmentation is accomplished using a superpixel clustering algorithm. Then, feature extraction is performed on the segmented images to extract deep learning features using an enhanced GWO based AlexNet model for better forgery detection. In the enhanced GWO technique, multi-objective functions are used for selecting the optimal hyper-parameters of AlexNet. Based on the obtained features, the adaptive matching algorithm is used for locating the forged regions in the tampered images. Simulation outcome showed that the proposed model is effective under the conditions: salt & pepper noise, Gaussian noise, rotation, blurring and enhancement. The enhanced GWO based AlexNet model attained maximum detection accuracy of 99.66%, 99.75%, and 98.48% on MICC-F600, MICC-F2000 and GRIP datasets.

show abstract

“…It is known that a higher F 1 score denotes performance better. Finally, the experiments are implemented on a computer with an Intel (R) Core i7-8700 @3.20 There are several state-of-the-art methods, including the Dense moment feature index and best match algorithm with radial-harmonic-Fourier moments (DMFIBM) (Zhong et al 2020), Bestagini et al (Bestagini et al 2013), MRPL method (Saddique et al 2020). However, the methods in the literatures of (Subramanyam and Emmanuel 2012) cannot be applied to real datasets like GRIP because they are with very restrictive assumptions on forgery videos.…”

Section: A Datasets For Video Copy-move Forgery Detectionmentioning

confidence: 99%

“…Video copy-move forgery achieves an excellent visual effect but requires relatively complex manipulation, that can be done with inter-frame and intra-frame (Zhong et al 2020). Inter-frame forgery pastes the copied objects from one frame to other corresponding frames in the video, while intra-frame forgery involves successive operations of pasting one or some copied objects from one frame into the same frame.…”

Section: Introductionmentioning

confidence: 99%

A fast forgery frame detection method for video copy-move inter/intra-frame identification

Zhong

Gan

Yang

2021

J Ambient Intell Human Comput

Self Cite

View full text Add to dashboard Cite

Digital video is critical visual evidence in various fields and is easily manipulated under different techniques such as the popular video copy-move forgery. In the past decades, although machine intelligence has been widely adopted to detect the forgery in digital images automatically, It still remains a very challenging detection task for carefully-crafted copy-move forgery in digital video for three reasons: (i) A video of medium length containing hundreds of frames already incurs a prohibitive computational cost; (ii) Similar backgrounds in contiguous frames are easily mistakenly detected as copy-move forgery regions, resulting to a large number of false alarms; (iii) Most state-of-the-art methods cannot detect video copymove inter-frame or intra-frame forgeries; To effectively address these issues, a fast forgery frame detection method for video copy-move inter/intra-frame identification is proposed: (i) The sparse feature extraction and matching speed-up the algorithm processing and reduce the time cost greatly (Defect (i)); (ii) The adaptive two-pass filtering and copy-move frame-pair matching can address the similarity problem (Defect (ii)) to locate truly forgery frame-pairs (FFP); (iii) Based on the results of these FFP, the type of video copy-move forgery detection can be identified (Defect (iii)). Furthermore, the copy-move frame-pair matching algorithm locates truly FFP, thus further reducing the computation cost and false alarm for detecting the inter/intra-frame forgery efficiently and effectively (Defect (i)). Finally, based on the truly FFP, the video can be checked for forgery or original. If there is no truly FFP, the video is considered as the original one. Otherwise, the video is checked if the forgery is inter-frame (i.e., truly FFP frames are two different frames) or intra-frame (the same frame). The experimental results show that our proposed algorithm achieves higher detection accuracy and higher robustness (false alarm = 2 and F 1 = 0.90) in the whole GRIP dataset than the existing state-of-the-art methods under various adverse conditions. KeywordsA fast forgery frame detection • Video copy-move inter/intra-frame identification • Sparse feature extraction and matching • Two-pass filtering • Copy-move frame-pair matching * Yan-Fen Gan

show abstract

Dense moment feature index and best match algorithms for video copy-move forgery detection

Cited by 28 publications

References 30 publications

Raven finch optimized deep convolutional neural network model for intra‐frame video forgery detection

Raven finch optimized deep convolutional neural network model for intra‐frame video forgery detection

Copy-Move Forgery Detection Using Superpixel Clustering Algorithm and Enhanced GWO Based AlexNet Model

A fast forgery frame detection method for video copy-move inter/intra-frame identification

Contact Info

Product

Resources

About