REVIEW ON SECURE DATA MANAGEMENT USING FACE MORPHING

Abstract

We proposed an image morphing based method for information embedding. The basic idea is to hide a secrete data into a morphed image which is obtained from the secrete image and another reference image. To make this method practically useful, it is essential to produce natural morphed images. This is a necessary condition conceal the existence of the secret image. To produce natural morphed images, we should select a proper feature point set (FPS) for morphing. This is a monotonous work if we do it manually, because the number of possible FPSs is very large. To solve the problem more efficiently, we adopted proposed interactive algorithm in this study and conducted experiments for generating morphed images. Results show that, if we provide a relatively good initial FPS, proposed interactive algorithm can fine-tune the FPS, and produce more natural images with limited number of iteration.