Description

Detection of forgery in images has numerous applications in forensics. The copy move forensic in images changes the original pixel informations from the images. The pixel informations that were changed were identified. In this proposed approach the forensic in the photography mainly copy move changes were analyzed. Initially take the original and Forgery image for input. Features will be extracted from original and forgery image using affine transformation. Perform patch matching process between original and forgery features which was extracted using affine transformation. Based on the patch matching process can segment forgery portion from forged image. Measure the performance for precision and recall based on the detection of forgery image. In this proposed system, original image and forgery image have been taken as input for detecting forgery portion. The above mentioned task performed by the affine transformation. An affine transformation or affine map is a function between affine spaces which preserves points, straight lines and planes. Also, sets of parallel lines remain parallel after an affine transformation. An affine transformation does not necessarily preserve angles between lines or distances between points, though it does preserve ratios of distances between points lying on a straight line. Perform patch matching process based on the extracted points and detect the forgery portion. Analysis the performance in terms of precision and recall. The patch based matching helps in locating the forged pixels more exactly in the images. The identification of the most interested points helps in reducing the time in checking each and every pixel of the image. The application of the affine transformations for the identification of the similarities in the images were capable for the identification of the interested points in the images more effectively. The calculated performances indicates that the proposed method is capable for the identification of copy move forgery in the images with greater accuracy.