Description

An effective method for the detection of forgery in images is proposed. In recent years, digital images are in use in a wide range of applications and for multiple purposes. They also play an important role in the storage and transfer of visual information, especially the secret ones. With this widespread usage of digital images, in addition to the increasing number of tools and software of digital images editing, it has become easy to manipulate and change the actual information of the image. Therefore, it has become necessary to check the authenticity and the integrity of the image by using modern and digital techniques, which contribute to analysis and understanding of the images’ content, and then make sure of their integrity. There are many types of image forgery, the most important and popular type is called copy move forgery, which uses the same image in the process of forgery. This type of forgery is used for one of two things, first to hide an object or scene by copying the area of the image and pasting it on another area of the same image. The second is the repetition of object or scene with change in some qualities “such as size” by copying this object and pasting it on another area of the same image. The copy paste forgery in the input images can be identified with the help of segmentation feature extraction and feature matching process. The input images were initially over segmented with the help of the SLOC algorithm. The features were extracted from each blocks based on Scale Invariant feature extraction algorithm (SIFT). From the extracted features the forgery is detected based on block matching and labeled feature point matching. In block matching process the distance between the divided images regions were identified. From the identified similarity between the features the copy move regions were identified in the image. The performance of the process is measured with the help of precision, recall and F-measure of the input image.