Local Gravity Face for Illumination Invariant and Heterogeneous Face Recognition in Matlab

Local Gravity Face for Illumination Invariant and Heterogeneous Face Recognition in Matlab

Abstract:

Region duplication or copy move forgery is a common type of tampering scheme carried out to create a fake image. The field on blind image forensics depends upon the authenticity of the digital image. As in copy move forgery the duplicated region belongs to the same image, the detection of tampering is complex as it does not leave a visual clue. But the tampering gives rise to glitches at pixel level. In the proposed work, we use the feature extraction method which emphasizes on the color content of the forged image. To explore on the color contents of the forged image, HSV Color space and color moments of the tampered image is analyzed. The proposed method works effectively on two different databases and the experimental results shows significant accuracy in detection of the forged region. The scheme is also successful in detection of forgery for images which are subjected to transformation and also effectively detects multiple copy move forgery attacks.