An Improved Data-hiding Approach using Skin-tone Detection for Video Steganography

Abstract

The secure transmission of data over internet is attained using steganography. It is an art and science of hiding information in undistinguishable cover media so as not to instigate and observer’s suspicion. Steganography is a method to secure the secret information by just embedding the information within other information. Several types or formats of steganography are being used in modern era such as, image, text and audio/video. There are several steganography algorithms each having its own weakness or strength in terms of complexity and security. Some of them provide invisibility of secret information while some provides large embedding capacity. Securing the embedded data and diminishing the distortions in videos remain as challenging goals in data-hiding techniques. In this work, a steganographic approach is proposed to minimize the probability of detection of the embedded image data in cover video objects where human skin regions are considered as Regions of Interest (ROI) for embedding the secret data. The proposed technique works with both 2-D and 3-D secret images, which increases the adaptability of the proposed model to the various types of image data. Selective continuous pixel stacks are used to embed the secret data in the cover video object, which is performed over the third Discrete Wavelet Transform (DWT) component. The approximation coefficient has been entitled to be utilized for the purpose of embedding after the application of third Level DWT over the input video frame to enhance robustness and video quality. The frame matrix further undergoes the skin-map extraction to make the color-based pixel selection. Moreover, the proposed approach is designed with the amalgamation of 8-pixel stack extraction on the third Level DWT over the Red and Blue channels. Experimental results reveal that the proposed data-hiding scheme offers high imperceptibility and enhance the robustness against MPEG-4 compression.