Novel Neural Network Based CT-NSCT Watermarking Framework Based upon Kurtosis Coefficients
- PDF / 3,603,459 Bytes
- 25 Pages / 439.37 x 666.142 pts Page_size
- 37 Downloads / 145 Views
Novel Neural Network Based CT‑NSCT Watermarking Framework Based upon Kurtosis Coefficients M. F. Kazemi1 · M. A. Pourmina2 · A. H. Mazinan3 Received: 6 January 2018 / Revised: 15 November 2019 © Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract In the research presented here, the novel neural network based watermarking framework is investigated in the area of transformation, while contourlet transform and nonsubsampled contourlet transform are realized to address the proposed idea via the Kurtosis to choose the band of suitable coefficients. It is to note that there are a number of techniques to deal with the aforementioned watermarking framework through the new integration of contourlet transform and nonsubsampled contourlet transform in connection with the perceptron neural network to extract the logo information, appropriately. There is the optimization technique through the genetic algorithm to provide the optimum results in the procedure of designing, as well. The approaches of the embedding and the de-embedding in case of learning algorithm of the neural network via individual training data set are considered in the present research to carry out a series of experiments with different scenario for the purpose of verifying the proposed techniques, obviously. Keywords Watermarking framework · Nonsubsampled contourlet transform · Neural network · Kurtosis coefficients
1 Introduction The subject behind the present research is to consider a new robust image watermarking utilizing contourlet transform (CT) in line with nonsubsampled contourlet transform (NSCT) that are organized to deal with the proposed framework via * A. H. Mazinan [email protected] 1
Department of Electrical Engineering, Lahijan Branch, Islamic Azad University (IAU), Lahijan, Iran
2
Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University (IAU), Tehran, Iran
3
Department of Control Engineering, Faculty of Electrical Engineering, South Tehran Branch, Islamic Azad University (IAU), No. 209 North Iranshahr St., P.O. Box 11365/4435, Tehran, Iran
13
Vol.:(0123456789)
7
Page 2 of 25
Sensing and Imaging
(2020) 21:7
the Kurtosis to choose the band of coefficients. There is a focus on the realizations of the CT, NSCT and also CT-NSCT, respectively, to present the research with respect to state-of-the-art, appropriately. It is to note that the main idea of the proposed watermarking framework is suggested in this research via the embedding and de-embedding techniques, while a series of attacks are applied to the outcomes for the purposed of presenting an applicable and efficient approach to be useful in real environments. In a word, the approach is an integration of new embedding and de-embedding approaches, as long as the efficiencies of the CT in association with the NSCT are directly used to generate watermarked image and the corresponding extracted logo image with high accuracy. It is to note that there is a technique of analyzing the performance to present bot
Data Loading...
