Optimized Features of SIFT Transform Function for Digital Image Watermarking using Hybrid Swarm Intelligence and Neural Network

Abstract

Authentication of digital multi-media is a challenging task in the current scenario of internet technology for the authentication of digital multi-media data used digital watermarking techniques. The feature-based watermarking techniques provide the robustness of digital watermarking methods. In this paper proposed optimized features based digital watermarking techniques using a neural network. For the process of features, optimization used hybrid swarm intelligence algorithms. The hybrid algorithms are a combination of PSO and ACO. The PSO used as feature optimizer and ACO used for the selection of features point for the processing of neural network models. Two neural networks models used BP and RBF. The property of both models is different for the processing of data and desired output for the enhancement of the proposed model used cascaded neural network models using BP and RBF. The cascaded models generate dynamic patterns for the embedding of a digital watermark. The dynamic patterns provide the randomness of the pixel value and decrease the value of attack predication. The proposed algorithms have been tested on an extensive database of 300 images. The analysis of the proposed algorithm is satisfactory against different types of attacks and enhance the strength of robustness.