DIFFERENT ZERO-WATERMARKING OF MEDICAL IMAGES FOR THE INTERNET OF MEDICAL THINGS

Abstract

Accuracy, dependability, and productivity of electronic devices in healthcare systems can
all be improved with the use of the Internet of Medical Things (IoMT). This study offers rapid,
numerous MFrLFMs, which stand for Multi-channel Fractional Legendre Fourier Moments, are the
basis of zero-watermarking systems for Internet of Medical Things (IoMT) applications that respect
the original medical pictures' confidentiality and copyright protection. In order to safeguard without
altering the original medical images, IoMT applications must respect medical image confidentiality
and copyright. Using MFrLFMs, or multi-channel fractional Legendre Fourier Moments, this study
presents simple techniques for multi-zero watermarking. The owner-share was produced by XORing
a binary scrambled watermark with the scrambled data using a two-dimensional discrete henon map
based on the most important features generated by MFrLFMs.The excellent reliability and high
accuracy states of neural networks like multilayer perceptions (MLP) have been the major topic of
numerous articles. Contemporary apps for precise classifiers and pattern recognition provide this.
This research study used the specialised machine learning approach known as the "convolution
neural network (CNN)" in order to increase the privacy security procedure within the validation
system. The input image is mostly necessary to provide appropriate working performance and to
decrease the amount of processed data. The pertinent Various image processing tasks, such as image
enlargement, image partitioning, and factor extraction, were successfully achieved.