Image forgery detection for high resolution images using SIFT and RANSAC algorithm

원문 초록

Cloning (copy-move forgery) is a malicious tampering attack with digital images where a part of image is copied and pasted within the image to conceal the important details of image without any obvious traces of manipulation. This type of tampering attacks leaves a big question of authenticity of images to the forensics. Many techniques are proposed in the past few years after powerful software’s are developed to manipulate the image. The proposed scheme is involved with both the block based and feature point extraction based techniques to extract the forged regions more accurately. The proposed algorithm mainly involves in matching the tentacles of same features extracted from each block by computing the dot product between the unit vectors. Random Sample Consensus (RANSAC) algorithm is used to extract the matched regions. The experimental result of the algorithm which is proposed indicates that, it can extract more accurate results compared with existing forgery detection methods.