Watermarking for medical images

Abstract

Medical images are more typical than any other ordinary images. In telemedicine newlineapplications, transmission of medical image via open channel, demands strong security newlineand copyright protection. Therefore, the security and authenticity of medical data can newlinebe enhanced and ensured by means of watermarking scheme, which is essential for newlinediagnosis and can be used as further reference. This thesis discusses a safe and secure newlinewatermarking technique using a machine learning algorithm. Additionally, it also newlinecovers algorithm for classification of RONI and ROI in the medical image for secure newlinedata embedding, so that diagnosis part remains unaffected. Although, nobody has newlineperformed SVM for classification in transform domain for medical image newlinewatermarking based on existing literature reviewed. newlineIn this thesis, propagation of watermarked image is simulated over a 3GPP/LTE newlinedownlink physical layer. In our proposed robust watermarking model, a double layer newlinesecurity is introduced to ensure the robustness of embedded data and then a transform newlinedomain-based hybrid watermarking technique, embeds the scrambled data into the newlinetransform coefficients of the cover image. Support Vector Machine (SVM) is work as newlinea classifier, which classify a medical image into two distinct areas i.e. Non-Region of newlineInterest (NROI) and Region of Interest (ROI). The secure watermark information is newlineembedded into the unimportant part of the medical image, using the proposed newlineembedding algorithm. The objective of the projected model is to avoid any quality newlinedegradation to the medical image. The result achieved in this simulation reveal that 10- newline6 newline Bit Error Rate (BER) value is realizable for greater value of Signal to Noise Ratio newline(SNR) i.e. more than 10.4 dB of SNR. The Peak Signal to Noise Ratio (PSNR) of newlinereceived cover image is more than 35 dB, which is acceptable for clinical applications. newlineTelemedicine is a renowned application, where the public network is used to transfer newlinethe huge amount of medical data. This transfer of medical data ought to be performed newlinesecurely