SVD BASED SKIN TONE STEGANOGRAPHY FOR SECURED COMMUNICATION

Abstract

Steganography is the art of hiding the existence of data in another transmission medium to achieve secret & secure communication. Steganography method used in my work is based on biometrics and the biometric feature used to implement steganography is skin tone region of images. Here secret data is embedded within skin region of image that will provide an excellent secure location for data hiding. For this skin tone detection is performed using HSV (Hue, Saturation and Value) color space. Additionally secret data embedding is performed using frequency domain approach - DWT (Discrete Wavelet Transform) combined with SVD (Singular value decomposition). The secret data is divided into two parts and SVD is applied to two high frequency sub bands of DWT. The singular value of both the sub bands is changed with half of the secret image and applied SVD to them. Then perform inverse DWT using two sets of modified DWT coefficients and two sets of non modified DWT coefficients. Finally, merge this skin region in which the embedding is done with the non skin pixel (rest of the unchanged image region) to obtain stego image. Same procedure is followed for the extraction of the secret image as well. For experiment purpose, I have considered the colored Cover image and gray scale secret image of size 256x256 and determined PSNR,MSE & Nc. Experiment results shows stego image is visually indistinguishable from the cover image.