Image watermarking techniques are used to provide copyright protection and verify ownership of media/entities. This technique refers to the concept of embedding of secret data/information of an owner in a given media/entity for determining any ownership conflicts that can arise. Many watermarking approaches have been offered by various authors in the last few years. However, there are not enough studies and comparisons of watermarking techniques in soft computing environments. Nowadays, soft computing techniques are used to improve the performance of watermarking algorithms. This paper surveys soft computing-based image watermarking for several applications. We first elaborate on novel applications, watermark characteristics and different kinds of watermarking systems. Then, soft computing based watermarking approaches providing robustness, imperceptibility and good embedding capacity are compared systematically. Furthermore, major issues and potential solutions for soft computing-based watermarking are also discussed to encourage further research in this area. Thus, this survey paper will be helpful for researchers to implement an optimized watermarking scheme for several applications.

Image watermarking using soft computing techniques: A comprehensive survey

The leapfrog development of computer technology has greatly enhanced the breadth of information dissemination. As a larger information carrier, color image becomes more and more popular, but the copyright protection problem becomes more and more serious. To solve this problem, this paper proposes a fusion-domain color watermarking based on Haar transform and image correction. Firstly, the maximum energy coefficient of Haar transform is directly obtained in spatial domain. Then, the coefficient is quantified with the help of variable quantization steps to embed the color watermark that encrypted by affine transform. If the watermarked image is processed by geometric attack, then the attacked image can be corrected by using of the geometric properties. Finally, the inverse embedding process is performed to extract the watermark. The performances of the proposed method are shown as follows: 1) all PSNR (Peak Signal-to-Noise Ratio) values are greater than 40 dB; 2) all SSIM (Structural Similarity Index Metric) values are greater than 0.96; 3) most NC (Normalized Cross-correlation) values are more than 0.9; 4) the key space is more than 2432; 5) the maximum embedded capacity is 0.25bpp; 6) the running time is about 6 s. Compared with the related methods, the experimental results show that the proposed method is feasible and has good performance.

A fusion-domain color image watermarking based on Haar transform and image correction

In this chapter, an improved color image watermarking method is presented where the logistic maps were utilized with the quaternion Legendre-Fourier moments (Logistic maps–QLFMs). An exact, highly accurate, fast and numerically stable method is used to compute the Logistic maps–QLFMs in polar coordinates. In the Logistic maps–QLFMs method, the radial and angular kernels are computed over circular pixels by using analytical integration. Based on the geometric invariance of QLFMs, the robustness of the Logistic maps–QLFMs method is improved against geometric attacks, and the logistic mapping is used to randomly select QLFMs coefficients. Therefore, selected QLFMs are quantized to embed the binary digital watermark in the host color image. Moreover, the Logistic maps–QLFMs watermarking method is compared with quaternion Legendre-Fourier moments and existing quaternion methods. The QLFMs method is computed by using the same computation of the Logistic maps–QLFMs method. Utilizing an efficient computational method, the radial kernels of existing quaternion are computed using the accurate Gaussian quadrature method while the angular kernel is computed using analytical integration with the same as Logistic maps–QLFMs and QLFMs methods. Numerical experiments are performed where the performance of Logistic maps–QLFMs method is compared with the existing quaternion moment-based watermarking methods in terms of visual imperceptibility and robustness against different attacks. The comparison clearly shows that the Logistic maps–QLFMs is outperformed than existing quaternion moment-based watermarking methods.

Improved Color Image Watermarking Using Logistic Maps and Quaternion Legendre-Fourier Moments

Computation-efficient image watermarking architecture with improved performance

A blind extraction watermarking method on color images is designed to protect © & identify owner of multimedia. Watermark in color is exploited to deliver universality and boundless applicability to proposed watermarking method. The host data is decomposed by applying four decomposition techniques like Discrete Wavelet Transform (DWT), QR, SVD & Schur decomposition. Arnold transformed watermark is utilized for better security. This scheme embed’s color watermark into gray-scale cover image which will be out of attacker’s expectation. A probabilistic neural network (PNN) is utilized in the watermark extraction. Robustness and quality of scheme are evaluated with quality measurement functions like Peak Signal to Noise Ratio (PSNR) and Normalized Correlation Coefficient (NCC).

Multiple Decompositions-Based Blind Watermarking Scheme for Color Images

A Discrete Rajan Transform-based robustness improvement encrypted watermark scheme backed by Support Vector Machine

COVID-19 is known in recent times as a severe syndrome of respiratory organ (Lungs) and has gradually produced pneumonia, a lung disorder all around the world. As coronavirus is continually spreading rapidly globally, the computed tomography (CT) technique has been made important and essential for quick diagnosis of this dangerous syndrome. Hence, it is necessitated to develop a precise computer-based technique for assisting medical clinicians in identifying the COVID-19 influenced patients with the help of CT scan images. Therefore, the multilayer perceptron neural networks optimized with Garra Rufa Fish optimization using images of CT scan is proposed in this paper for the classification of COVID-19 patients (COV-19-MPNN-GRF-CTI). The input images are taken from SARS-COV-2 CT-scan dataset. Initially, the input images are pre-processed utilizing convolutional auto-encoder (CAE) to enhance the quality of the input images by eliminating noises. The pre-processed images are fed to Residual Network (ResNet-50) for extracting the global and statistical features. The extraction over the features of CT scan images is made through ResNet-50 and subsequently input to multilayer perceptron neural networks (MPNN) for CT images classification as COVID-19 and Non-COVID-19 patients. Here, the layer of Batch Normalization of the MPNN is separated and added with ResNet-50 layer. Generally, MPNN classifier does not divulge any adoption of optimization approach for calculating the optimal parameters and accurately classifying the extracted features of CT images. The Garra Rufa Fish (GRF) optimization algorithm performs to optimize the weight parameters of MPNN classifiers. The proposed approach is executed in MATLAB. The performance metrics, such as sensitivity, precision, specificity, [Formula: see text]-measure, accuracy and error rate, are examined. Then the performance of the proposed COV-19-MPNN-GRF-CTI method provides 22.08%, 24.03%, 34.76% higher accuracy, 23.34%, 26.45%, 34.44% higher precision, 33.98%, 21.95%, 34.78% lower error rate compared with the existing methods, like multi-task deep learning using CT image analysis for COVID-19 pneumonia classification and segmentation (COV-19-MDP-CTI), COVID-19 classification utilizing CT scan depending on meta-classifier approach (COV-19-SEMC-CTI) and deep learning-based COVID-19 prediction utilizing CT scan images (COV-19-CNN-CTI), respectively. 

Classification of COVID-19 Patient based on Multilayer Perceptron Neural Networks Optimized with Garra Rufa Fish Optimization using CT Scan Images

Video capsule endoscope (VCE) is a developing methodology, which permits analysis of the full gastrointestinal (GI) tract with minimum intrusion. Although VCE permits for profound analysis, evaluating and analyzing for long hours of images is tiresome and cost-inefficient. To achieve automatic VCE-dependent GI disease detection, identifying the anatomical region shall permit for a more concentrated examination and abnormality identification in each area of the GI tract. Hence we proposed a hybrid (Long-short term memory-Visual Geometry Group network) LSTM-VGGNET based classification for the identification of the anatomical area inside the gastrointestinal tract caught by VCE images. The video input data is converted to frames such that the converted frame images are taken and are processed. The processing and classification of health condition data are done by the use of Artificial intelligence (AI) techniques. In this paper, we proposed a prediction of medical abnormality from medical video data that includes the following stages as given: Pre-processing stage performs using Gabor filtering, histogram-based enhancement technique is employed for the enhancement of the image. Multi-linear component analysis-based feature selection is employed, and the classification stage performs using Hybrid LSTM-VGGNET with the performance of accurate prediction rate. 

Anatomical Region Detection Scheme Using Deep Learning Model in Video Capsule Endoscope

The majority of systems on the market today are made up of intricate SoCs with integrated processors, large quantities of memory and FPGAs, but they do not offer a complete system solution for real-world systems [1]. Designers are faced with numerous technological and financial obstacles when attempting to combine such different technologies onto a single chip [2]. Additionally, vertical integration was shown to be a desirable alternative due to the continuously growing needs for low cost, smaller chips with more capability, and shorter time to market for portable systems [3]. Three-dimensional integration is the vertical interconnection of unpackaged or packaged semiconductors [3]. The most promising technique for designing ICs and systems with high performance, functionality, and lower power consumption than the 2D technologies is three dimensional integrated circuits (IC) in the form of three-dimensionally stacked chips. Using inter-tier interconnects that directly cross the substrate, various dice can be joined in 3D integration [4]. This is referred as Through Silicon Via (TSV) based 3D integration technology. To provide uniform environmental conditions throughout all tiers, TSV tapering is done to achieve the least amount of voltage drop and delay difference possible. When the resistance values and current demand for each tier are known, thevenin network architecture may be used for TSV sizing.

S. Vairaprakash

Papers

A Discrete Rajan Transform-based robustness improvement encrypted watermark scheme backed by Support Vector Machine

Classification of COVID-19 Patient based on Multilayer Perceptron Neural Networks Optimized with Garra Rufa Fish Optimization using CT Scan Images

Anatomical Region Detection Scheme Using Deep Learning Model in Video Capsule Endoscope

Modelling and Analysis of different types of TSV for Three Dimensional Integrated Circuits