Machine Learning-Based Robust Watermarking Technique for Medical Image Transmitted Over LTE Network

Abstract

Abstract This paper discusses a safe and secure watermarking technique using a machine learning algorithm. In this paper, the propagation of a watermarked image is simulated over the third-generation partnership project (3GPP)/long-term evolution (LTE) downlink physical layer. The watermark data are scrambled and a transform domain-based hybrid watermarking technique is used to embed this watermark into the transform coefficients of the host image and transmitted over the orthogonal frequency division multiplexing (OFDM) downlink physical layer. Support vector machine (SVM) is used as a classifier for the classification of non-region of interest (NROI) and region of interest (ROI) in a medical image. The result achieved in this experiment revealed that a 10−6 bit error rate (BER) value is realizable for a greater value of signal-to-noise ratio (SNR; i.e. more than 10.4 dB of SNR). The peak SNR (PSNR) of the received cover image is more than 35 dB, which is acceptable for clinical applications.