An Improved Block Based Copy-Move Forgery Detection Technique

Abstract

With the increase in demand of identification of authenticity of the digital images, researchers are widely studying the image forgery detection techniques. Copy-move forgery is amongst the commonly used forgery, which is performed by copying a part of image and then pasting it on the same or different image. This results in concealing of image content. Most of the existing copy-move forgery detection techniques are subjected to degradation in results, under the effect of geometric transformations. In this work, a Discrete Cosine Transformation (DCT) and Singular Value Decomposition (SVD) based technique is proposed to detect the copy-move image forgery. DCT is used to transform the image from spatial domain to frequency domain and SVD is used to reduce the feature vector dimension. Combination of DCT and SVD makes the proposed scheme robust against compression, geometric transformations and noise. For classification of images as forged or authentic, Support Vector Machine (SVM) classifier is used on the feature set. Once the image is detected as forged, then for the localization of forged region, K-means clustering is used on the feature vector. According to distance threshold, similar blocks are identified and marked. The application of SVD provides the stability and invariance from geometric transformations. SVM classifier classifies the images as forged or authentic. Evaluation of the proposed scheme is done with and without post-processing operations on the images, both at pixel level and image level. Pixel level analysis shows the accuracy of proposed scheme in detecting forgery within an image. Image level analysis shows the accuracy of proposed scheme in image classification whether it is forged or original. The proposed scheme outperforms the various state-of-the-art techniques of Copy-Move Forgery Detection (CMFD) in terms of accuracy, precision, recall and F1 parameters. Moreover, the proposed scheme also provides better results against various attacks such as rotation, scaling, noise addition and JPEG compression.