Reversible Data Hiding in Medical Image for Contrast Enhancement of ROI

Reversible data hiding is a kind of information hiding technique that can exactly recover the original image through data hiding and extraction. It can be potentially used in the medical and military applications. In the literature, by using the maximum inter-class square error to separate the background and foreground, the principal gray-scale values in the segmented background can be identified. By excluding the corresponding histogram bins from being expanded, the contrast of region of interest (ROI) in medical images can be selectively enhanced. In this paper, a new method is proposed to get the foreground contour to enhance the contrast of ROI in medical images, while the original image can be exactly recovered when needed. The experimental results on a set of medical images show that the visibility of ROI can be improved. Compared with the previous method, the proposed method can achieve better contrast enhancement effects and visual quality.