ROI-based fragile medical image watermarking technique for tamper detection and recovery using variance

Protection of medical images using watermarking is an imperative area of research. In telemedicine, medical images are exchanged between distant places through unsecure networks like internet for diagnosis purpose. During this transfer, medical images may be tampered intentionally or accidentally. The medical practitioner has to check the integrity of Region of Interest (ROI) in the received medical image before making any diagnostic decisions. In this paper, we are developing a novel fragile and block based medical image watermarking technique for producing high quality watermarked medical images, verifying the integrity of ROI, detecting accurately the tampered blocks inside ROI using both average and variance of blocks and recovering the original ROI with zero loss. In the proposed method, the medical image is segmented into three sets of pixels: ROI pixels, Region of Non Interest (RONI) pixels and border pixels. Then, authentication data and information of ROI are embedded in border pixels. Recovery data of ROI is embedded into RONI. Results of experiments conducted on number of medical images reveal that proposed method produces high quality watermarked medical images, identifies the presence of tampers inside ROI of watermarked medical images with 100% accuracy and recovers the original ROI without any loss.