Novel Neural Network Based CT-NSCT Watermarking Framework Based upon Kurtosis Coefficients

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.