Abstract: Digital Images are source of information. In Image Forensics, the detection of copy- move forgery detection has received much more attention. In the case of Copy- Move Forgery, the same part of the image is copied and pasted into some other parts of the same image itself. So, it is very difficult to identify such forged regions since the color, contract and other features are almost similar to the original image. In this work, the copy –move forgery detection is identified using Adaptive Oversegmentation and feature point matching. It combines the advantages of both Block based and Keypoint based forgery detection techniques. The image is divided into different blocks using Adaptive Oversegmentation. Then, the feature points are extracted from each block as block features, and the block features are matched with one another. If the match value exceeds the predefined threshold value, the suspected forgery regions will be indicated. Merged Regions are extracted using Forgery Region Extraction Algorithm. To generate the detected forgery regions the morphological operation is applied to the merged regions.

Keywords: Feature point, Forgery, Image, Keypoint, Oversegmentation

Open chat
Chat with IJARCCE