Boosting Image Forgery Detection using Resampling Features and Copy-move Analysis

Mohammed, Tajuddin Manhar; Bunk, Jason; Nataraj, Lakshmanan; Bappy, Jawadul H.; Flenner, Arjuna; Manjunath, B. S.; Chandrasekaran, Shivkumar; Roy-Chowdhury, Amit K.; Peterson, Lawrence

doi:10.2352/issn.2470-1173.2018.07.mwsf-118

Cited by 22 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent efforts, including [8], [9], [17], [62], [77] in the manipulation detection task, exploit deep learning based models. These tasks include detection of generic manipulations [8], [9], resampling [10], splicing [77], and bootleg [16].…”

Section: Related Workmentioning

confidence: 99%

Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries

Bappy

Simons

Nataraj

et al. 2019

IEEE Trans. on Image Process.

Self Cite

368

207

View full text Add to dashboard Cite

With advanced image journaling tools, one can easily alter the semantic meaning of an image by exploiting certain manipulation techniques such as copy-clone, object splicing, and removal, which mislead the viewers. In contrast, the identification of these manipulations becomes a very challenging task as manipulated regions are not visually apparent. This paper proposes a high-confidence manipulation localization architecture which utilizes resampling features, Long-Short Term Memory (LSTM) cells, and encoder-decoder network to segment out manipulated regions from non-manipulated ones. Resampling features are used to capture artifacts like JPEG quality loss, upsampling, downsampling, rotation, and shearing. The proposed network exploits larger receptive fields (spatial maps) and frequency domain correlation to analyze the discriminative characteristics between manipulated and non-manipulated regions by incorporating encoder and LSTM network. Finally, decoder network learns the mapping from low-resolution feature maps to pixel-wise predictions for image tamper localization. With predicted mask provided by final layer (softmax) of the proposed architecture, end-to-end training is performed to learn the network parameters through back-propagation using ground-truth masks. Furthermore, a large image splicing dataset is introduced to guide the training process. The proposed method is capable of localizing image manipulations at pixel level with high precision, which is demonstrated through rigorous experimentation on three diverse datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries

Bappy

Simons

Nataraj

et al. 2019

IEEE Trans. on Image Process.

Self Cite

368

207

View full text Add to dashboard Cite

show abstract

“…Mohammed et al [12] use the CNN to obtain the abnormal image boundary features and the LSTM to establish the connection between image patches. A separate detection model is used to obtain more accurate detection results to enhance the detection e ect of the copy-move manipulation image.…”

Section: Related Workmentioning

confidence: 99%

Semantic Modeling and Pixel Discrimination for Image Manipulation Detection

Xue

Jiang

Liu

2022

Security and Communication Networks

View full text Add to dashboard Cite

Image manipulation methods, such as the copy-move, splicing, and removal methods, have become increasingly mature and changed the common perception of “seeing is believing.” The credibility of digital media has been seriously damaged with the development of image manipulation methods. Most image manipulation detection methods detect traces of tampering pixel by pixel. As a result, the detected manipulation areas are separated, which results in insufficient consideration of content manipulation at the object level. In this paper, the detection of image manipulation areas based on forgery object detection and pixel discrimination is proposed. Specifically, the pixel-level detection branch resamples features and uses an LSTM to detect manipulations, such as resampling, rotation, and cropping. The goal of the forgery object detection branch, which is based on Faster R-CNN, is to extract the regions of interest and analyze the regions with high contrast as well as the forgery objects of the image. Furthermore, the fused heatmaps of the two branches are integrated with the object detection results. The noise in the heatmaps is shielded based on the forgery object information of the region proposal network. Experimental results on multiple standard forgery datasets have demonstrated the superiority of our proposed method compared with the state-of-the-art methods.

show abstract

“…Copy move counterfeiting is among a number of image manipulation methods that may be used to fabricate a photograph. Forgery committed using the copy move technique involves cutting off a section of a picture, copying and pasting it into a different location or locations inside the same shot (by whether or not altering the copied element of the image) [1]. The primary purpose of this form of forgery is to hide certain components or areas of the picture by replicating them [2].…”

Section: Introductionmentioning

confidence: 99%

Copy Move Forgery Detection: The Current Implications and Contemporary Practices

Gajjar

Saxena

Shah

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Copy move forgeries are a type of digital retouching that takes place in the field of image modification. This type of retouching occurs when one element of a picture is replicated over to a different segment of the photograph. This is typically done in an effort to mask or cover up undesirable qualities of the photograph thus copy move forgeries are a form of image modification. When it comes to digital picture modalities, copy move forging is by far the most prevalent form of picture manipulation that may take place. This is mainly observed when certain elements or segments of the recorded file are duplicated in the recorded file. The identification and localization of forgeries is a prominent problem that has piqued the attention of scholars working in the field of digital forensics and continues to do so. The identification of photo forgery has previously been the subject of several methodologies and uncountable publications, all of which were created and published. An abridged description of the present methodology and approaches is provided in this document, along with a survey and condensed summaries of current research and successes, among other things.

show abstract

Boosting Image Forgery Detection using Resampling Features and Copy-move Analysis

Cited by 22 publications

References 34 publications

Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries

Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries

Semantic Modeling and Pixel Discrimination for Image Manipulation Detection

Copy Move Forgery Detection: The Current Implications and Contemporary Practices

Contact Info

Product

Resources

About