Efficient Detection Technique for Image Forgery

V. Suresh, T. Primya, G. Kanagaraj

Abstract


Image forgery is a real time issue in this present era and causes a lot of tribulations to the society. The forgery in an image includes object addition, object removal, changing color etc.  The overture of our work is to find the type of forgery present in an image i.e. whether the image is retouched or copy move forgery. While comparing to copy move forgery, Retouching is not a major kind of forgery because it is used only for clarification purpose and also in this paper we are going to propose a fuzzy logic algorithm for segmentation of an image to improve the accuracy rate of detecting the cloned region in an image. Initially the image was segmented into patches and a keypoint was extracted in each patches. The detection of cloned region is done in two stages. In first stage, an affine transform matrix was built by finding the suspicious pairs in an image. In second stage, the detection of cloned region can be accurately detected using Fuzzy technique.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.