A Robust Watermarking Scheme Using Machine Learning Transmitted Over High-Speed Network for Smart Cities

Abstract

Medical images are more typical than any other ordinary images. In telemedicine applications, transmission of medical image via open channel, demands strong security and copyright protection. This paper discusses a safe and secure watermarking technique using a machine learning algorithm. In this paper, propagation of watermarked image is simulated over a 3GPP/LTE downlink physical layer. In our proposed robust watermarking model, a double layer security is introduced to ensure the robustness of embedded data and then a transform domain-based hybrid watermarking technique, embeds the scrambled data into the transform coefficients of the cover image. Support Vector Machine (SVM) is work as a classifier, which classify a medical image into two distinct areas i.e. Non-Region of Interest (NROI) and Region of Interest (ROI). The secure watermark information is embedded into the unimportant part of the medical image, using the proposed embedding algorithm. The objective of the projected model is to avoid any quality degradation to the medical image. The result achieved in this experiment reveal that 10−6 Bit Error Rate (BER) value is realizable for greater value of Signal to Noise Ratio (SNR) i.e. more than 10.4 dB of SNR. The Peak Signal to Noise Ratio (PSNR) of received cover image is more than 35 dB, which is acceptable for clinical applications.