SIMPLE LINEAR ITERATIVE CLUSTERING AND HAAR WAVELET BASED IMAGE FORGERY DETECTION

Abstract

The ready availability ofimage-editingsoftwaremakesitimportanttoensuretheauthenticity of images. This thesis concerns the detection and localization of cloning, or Copy-Move Forgery (CMF), which is the most common type of image tampering, inwhichpart(s)ofthe image are copied and pasted back somewhereelseinthesameimage.Post-processingcanbe used to produce more realistic doctored images and thus can increase the difficulty of detecting forgery.

The thesis postulates the use of segmentation approach by following the three steps, segmentation of the image by SLIC, then using the Haar Wavelet Transform to extract the features and then using the Dense Depth Reconstruction algorithmforfeaturematching.The experimental results illustrate that our proposed algorithms can detect forgery in images containing copy-move objects with different types of transformation (translation, rotation, scaling, distortion andcombinedtransformation).Moreover,theproposedmethodsarerobust to postprocessing (i.e. blurring, brightness change, color reduction, JPEG compression, variations in contrast and added noise) and can detect multiple duplicated objects.