Aboul Ella Hassanien (Abo)

In this paper, we propose a novel optimal singular value decomposition (SVD)-based image watermarking approach that uses a new combination of weighted quantum particle swarm optimization (WQPSO) algorithm and a human visual system (HVS) model for both the hybrid discrete wavelet transform and discrete cosine transform (DCT). The proposed SVD-based watermarking approach initially decomposes the host image into sub-bands; afterwards, singular values of the DCT of the lower sub-band of the host image are quantized using a set of optimal quantization steps deduced from a combination of the WQPSO algorithm and the HVS model. To evaluate the performance of the proposed approach, we present tests on different images. The experimental results show that the proposed approach yields a watermarked image with good visual definition; at the same time, the embedded watermark was robust against a wide variety of common attacks, including JPEG compression, Gaussian noise, salt and pepper noises, Gaussian filters, median filters, image cropping, and image scaling. Moreover, the results of various experimental analyses demonstrated the superiority of the WQPSO approach over other optimization techniques, including classical PSO and QPSO in terms of local convergence speed, resulting in a better balance between global and local searches of the watermarking algorithm.

In this paper we present a secure patient medical images and authentication scheme which enhances the security, confidentiality and integrity of medical images transmitted through the Internet. This paper proposes a watermarking by invoking particle swarm optimization (PSO) technique in adaptive quantization index modulation and singular value decomposition in conjunction with discrete wavelet transform (DWT) and discrete cosine transform (DCT). The proposed approach promotes the robustness and watermarked image quality. The experimental results show that the proposed algorithm yields a watermark which is invisible to human eyes, robust against a wide variety of common attacks and reliable enough for tracing colluders.

The sine cosine algorithm (SCA), a recently proposed population-based optimization algorithm, is based on the use of sine and cosine trigonometric functions as operators to update the movements of the search agents. To optimize performance, different parameters on the SCA must be appropriately tuned. Setting such parameters is challenging because they permit the algorithm to escape from local optima and avoid premature convergence. The main drawback of the SCA is that the parameter setting only affects the exploitation of the prominent regions. However, the SCA has good exploration capabilities. This article presents an enhanced version of the SCA by merging it with particle swarm optimization (PSO). PSO exploits the search space better than the operators of the standard SCA. The proposed algorithm, called ASCA-PSO, has been tested over several unimodal and multimodal benchmark functions, which show its superiority over the SCA and other recent and standard meta-heuristic algorithms. Moreover, to verify the capabilities of the SCA, the SCA has been used to solve the real-world problem of a pairwise local alignment algorithm that tends to find the longest consecutive substrings between two biological sequences. Experimental results provide evidence of the good performance of the ASCA-PSO solutions in terms of accuracy and computational time.