Dual branch convolutional neural network for copy move forgery detection

Abstract

The advent of digital era has seen a rise in the cases of illegal copying, distribution and forging of images. Even the most secure data channels sometimes suffer to validate the integrity of images. Forgery of multimedia data is devastating in various important applications like defence and satellite. Increased illegal tampering of images has paved way for research in the area of digital forensics. Copy move forgery is one of the various tampering techniques which is used for manipulating an image's content. A deep learning–based passive Copy Move Forgery Detection algorithm is proposed that uses a novel dual branch convolutional neural network to classify images as original and forged. The dual branch convolutional neural network extracts multi‐scale features by employing different kernel sizes in each branch. Fusion of extracted multi‐scale features is then performed to achieve a good accuracy, precision and recall scores. Experiment analysis on MICC F‐2000 dataset has been performed under two different kernel size combinations. Extensive result analysis and comparative analysis proves the efficacy of proposed architecture over existing architecture in terms of performance scores, computation time, and complexity.

Copy-Move Forgery Detection (CMFD) Using Deep Learning for Image and Video Forensics

“…However, it is not clear whether the classifiers are biased to one class, as few papers report all four metrics: acc , P , R and F1 . For instance, in [ 29 ] the authors reported a precision of 89.0% and recall of 100%, which implies that these metrics are not balanced, and specifically, the classifier is slightly biased to the positive class.…”

Image Hashing Through Spatio-triad Relationship

“…PRNU patterns have contributed to identify source camera [5][6][7][8][9]. Forgery localisation is achieved by abhishek et al, using semantic segmentation along with deep learning approach [10] Goel et al, used variant kernel size for dual branches to extract multiscale features that are later fused to obtain dominant features to assist classification of forged and authentic images [11]. 4 layer cnn is adopted with filter to detect splicing , copy-move [12].…”

Detection of Image Tampering Using Deep Learning, Error Levels & Noise Residuals

“…Goel et al [17] also used a dual-branch CNN to capture features from tampered images. Their technique was only to detect copy-move tampering and not image splicing.…”