Simple Clustering Research Articles

Effect of different defects on the polarization mechanism of (Nb,Ga) codoped TiO2 single crystals

Various defects have a profound impact on the dielectric properties and polarization mechanisms of (Nb,Ga) codoped TiO2 crystals. However, the research conducted in this area remains limited. To address this, we grew (Nb,Ga) codoped TiO2 crystals via the Verneuil method and investigated their dielectric properties under various atmospheric annealing conditions. Annealing in oxygen reduces the number of defects. In this case, the point defects associated with oxygen vacancies is unable to fully form the ideal complex defect clusters which can form effective pegging of free electrons. On the other hand, the defects are mainly in the form of simple defect clusters that causes hopping polarization. Annealing under mixed gas (Ar:H2 = 95%:5%) increases the number of defects and contains more free carriers, which migrate to the interface between the sample and the electrode, leading to interfacial polarization. Both hopping polarization and interfacial polarization are slow polarization, resulting in an increase in dielectric loss and a decrease in frequency stability. Annealing in air or nitrogen atmospheres forms ideal defect dipole clusters, where the electron-pinned defect dipoles (EPDD) are predominantly polarized, resulting in superior dielectric properties. It has been clarified that EPDD as the main polarization form can yield better dielectric properties. By focusing on single crystals as the research subject, we effectively eliminate the influence of grain boundaries, enabling a more accurate assessment of the effects of various crystal defects on dielectric properties. This study holds substantial implications for the advancement of TiO2-based dielectric materials, offering valuable insights into their performance optimization.

A no-reference panoramic image quality assessment with hierarchical perception and color features

The ultimate goal of no-reference omnidirectional image quality assessment (NR-OIQA) is to design a comprehensive perception method that can accurately assess the quality of damaged omnidirectional images without prior knowledge. However, most existing studies cannot attain credible accuracy because of lacking a non-neuroscience-based or non-biology-based model. Inspired by this, an original visual perception-based and neuroscience-based OIQA model by considering the hierarchical perception features of the HVS, which includes specific information, local saliency information, global information, and color information which is often ignored by researchers is proposed in this work. According to the hierarchical process in neuroscience, the high-frequency co-occurrence matrix (HFCM)-based and variance-based specific features are applied to perceive details that are first distorted in the frequency domain. The entropy-based combination of the paranormal saliency map(PSM) and superpixel segmentation with the simple linear iterative clustering (SLIC) algorithm is employed to emphasize the rich quality-aware local saliency information. The global panoramic statistical (GPS) model is utilized to express global semantics distortion as the high-level feature. Visual-aware color texture descriptor with the cross-channel local binary pattern(CCLBP) which effectively reflects the correlation and dependency of pixels between different color channels is employed to map color information. Finally, all above features have been extracted and combined with subjective scores to assess the objective quality scores by support vector regression (SVR). Experiments express that our method has more accuracy and stronger stability on CVIQD2018 and OIQA databases.

TCGAN: Convolutional Generative Adversarial Network for time series classification and clustering

Recent works have demonstrated the superiority of supervised Convolutional Neural Networks (CNNs) in learning hierarchical representations from time series data for successful classification. These methods require sufficiently large labeled data for stable learning, however acquiring high-quality labeled time series data can be costly and potentially infeasible. Generative Adversarial Networks (GANs) have achieved great success in enhancing unsupervised and semi-supervised learning. Nonetheless, to our best knowledge, it remains unclear how effectively GANs can serve as a general-purpose solution to learn representations for time series recognition, i.e., classification and clustering. The above considerations inspire us to introduce a Time-series Convolutional GAN (TCGAN). TCGAN learns by playing an adversarial game between two one-dimensional CNNs (i.e., a generator and a discriminator) in the absence of label information. Parts of the trained TCGAN are then reused to construct a representation encoder to empower linear recognition methods. We conducted comprehensive experiments on synthetic and real-world datasets. The results demonstrate that TCGAN is faster and more accurate than existing time-series GANs. The learned representations enable simple classification and clustering methods to achieve superior and stable performance. Furthermore, TCGAN retains high efficacy in scenarios with few-labeled and imbalanced-labeled data. Our work provides a promising path to effectively utilize abundant unlabeled time series data.

Identification of Structural and Morphogenesis Genes of Sulfitobacter Phage ΦGT1 and Placement within the Evolutionary History of the Podoviruses.

ΦGT1 is a lytic podovirus of an alphaproteobacterial Sulfitobacter species, with few closely matching sequences among characterized phages, thus defying a useful description by simple sequence clustering methods. The history of the ΦGT1 core structure module was reconstructed using timetrees, including numerous related prospective prophages, to flesh out the evolutionary lineages spanning from the origin of the ejectosomal podovirus >3.2 Gya to the present genes of ΦGT1 and its closest relatives. A peculiarity of the ΦGT1 structural proteome is that it contains two paralogous tubular tail A (tubeA) proteins. The origin of the dual tubeA arrangement was traced to a recombination between two more ancient podoviral lineages occurring ~0.7 Gya in the alphaproteobacterial order Rhizobiales. Descendants of the ancestral dual A recombinant were tracked forward forming both temperate and lytic phage clusters and exhibiting both vertical transmission with patchy persistence and horizontal transfer with respect to host taxonomy. The two ancestral lineages were traced backward, making junctions with a major metagenomic podoviral family, the LUZ24-like gammaproteobacterial phages, and Myxococcal phage Mx8, and finally joining near the origin of podoviruses with P22. With these most conservative among phage genes, deviations from uncomplicated vertical and nonrecombinant descent are numerous but countable. The use of timetrees allowed conceptualization of the phage's evolution in the context of a sequence of ancestors spanning the time of life on Earth.

Link quality and energy efficient optimal simplified cluster based routing scheme to enhance lifetime for wireless body area networks

Monitoring of patient’s health in the medical industry can be enabled using wireless body area networks (WBANs), which are already used for various purposes, including assisting in human safety. It is imperative to use better power management strategies since the body sensors are small and the battery cannot hold a charge for a long time. Due to the vast amounts of information generated by medical sensors, resource-constrained networks face a significant challenge when guaranteeing the specified quality of service (QoS). Moreover, the WBAN regularly meets the primary hassle of QoS degradation because of congestion WBAN structure can easily compromise heterogeneous and complex networks. Either inappropriate data collection or using energy effectively to transmit medical data without the expense of travel and length has become an important one. To address this issue, the present research work ‘Link Quality and Energy Efficient Optimal Clustering-Multipath (LEOC-MP)’ scheme tries to explore an answer. The main goals of the LEOC-MP (Optimal Link Quality and Energy Efficient Optimal Clustering-Multipath) system are to guarantee node-to-node link quality, lengthen network life, and compute high-performing cluster heads to guarantee reliable multi path data transfer. This work was executed in three phases. First, an optimal simplified clustering technique for data collection from body sensors using an improved pelican optimization (ICO) algorithm is introduced. Next, multiple design constraints for node rank computation, energy efficiency, link quality, path loss, distance, and delay are used. Besides, an Auto-Regressive Probabilistic Neural Network (AR-PNN) is introduced to optimize those design constraints and compute the cluster head (CH) of each cluster. Multipath firing is then performed using a moderated puffer-fish optimization (MPO) algorithm that finds the closest optimal and shortest node to transmit optimal drug data. The work is simulated using an NS-3 environment, and the results are obtained. The outcome of this work is analyzed with existing methodologies, and the results prove that the present work consistently outperforms the existing methodologies.

Mixture Based Superpixel Segmentation and Classification of SAR Images

Abstract: The proposed approach suggests a mixture-based super pixel segmentation technique for synthetic aperture radar (SAR) images. SAR is a radar system used to generate 2D or 3D representations of objects like landscapes. This method utilizes SAR image amplitudes and pixel coordinates as features. Super pixels are large irregular-shaped regions obtained through oversegmentation of an image. While super pixel segmentation methods are commonly designed for colour images, this approach adapts a finite mixture model (FMM) for single-channel SAR images. By employing finite mixture models, the pixels are clustered into super pixels. Following the super pixel segmentation, the method employs a hierarchical decision tree clustering algorithm for classifying different land covers, such as climate monitoring and natural resources exploitation. The decision tree algorithm creates a dendrogram or tree structure to group feature vectors. The proposed super pixel method demonstrates improved classification accuracy compared to state-of-the-art methods like quick-shift, turbo pixels, simple linear iterative clustering, and pixel intensity and location similarity. The implementation of the proposed method is efficiently carried out using MATLAB software.

Superpixel-Based Stripe Noise Removal for Satellite Imageries

This work introduces a novel noise removal algorithm for satellite imageries based on superpixel segmentation followed by statistics-based filtering. The algorithm worked in three main steps. First, the noisy input image was divided into subregions by employing simple linear iterative clustering (SLIC)-based superpixel segmentation. Then, the statistical property of each subregion was calculated, including their standard deviations and maximum values. Last, an adaptive statistics-based stripe noise removal was performed for each subregion by constructing adaptive filter sizes according to calculated properties. The algorithm was tested using real satellite imageries taken by the LAPAN-A2 and LAPAN-A3 satellites. Its performance was then compared to three existing methods in terms of image quality and computation speed. Extensive experiments on two datasets of 3-channel images captured by the LAPAN-A2 satellite showed that the algorithm was capable of reducing the stripe pattern as measured using the peak-signal-to-noise-ratio (PSNR) metric without introducing additional artifacts, which commonly appeared on over-corrected regions. Moreover, compared to existing methods, the proposed algorithm ran 42 to 103 times faster and provided better image quality by 2.46%, measured using the structural similarity metric (SSIM). The code of this work and the datasets used for the testing are publicly available on www.github.com/dancingpixel/SPSNR.

Theoretical Study on 10C Elastic Scattering Cross Sections Using Different Cluster Density Distributions and Different Potentials

Elastic scattering cross sections are a fundamental aspect of nuclear physics research, and studying the cross sections of various nuclei can provide important insights into the behavior of nuclei. In this study, the elastic scattering cross sections of 10C projectile by 27Al, 58Ni, and 208Pb target nuclei are analyzed. The aim of this study is to investigate the cluster structure of 10C and the sensitivity of the elastic scattering cross sections to different potentials. To achieve this objective, the double folding optical model and a simple cluster approach are used to analyze the cross sections. The real part of the optical potential is obtained by folding two different effective interactions, Michigan-3-Yukawa (M3Y) and JeukenneLejeune-Mahaux (JLM), with four different cluster density distributions of the 10C nucleus: 6Be + \alpha, 9B + p, 8Be + p + p, and \alpha + \alpha + p + p. The imaginary part is taken to be a Woods-Saxon phenomenological form. The sensitivity of the elastic scattering cross sections to different potentials is assessed by comparing the results obtained using different potentials. The cluster structure of 10C is validated by comparing the theoretical results with experimental data. The results show that the cross sections are sensitive to the choice of potential used and that the cluster structure of 10C is validated. The theoretical results show reasonable agreement with the experimental data.

A super-voxel-based method for generating surrogate lung ventilation images from CT.

Purpose: This study aimed to develop and evaluate , a super-voxel-based method for surrogate computed tomography ventilation imaging (CTVI). Methods and Materials: The study used four-dimensional CT (4DCT) and single-photon emission computed tomography (SPECT) images and corresponding lung masks from 21 patients with lung cancer obtained from the Ventilation And Medical Pulmonary Image Registration Evaluation dataset. The lung volume of the exhale CT for each patient was segmented into hundreds of super-voxels using the Simple Linear Iterative Clustering (SLIC) method. These super-voxel segments were applied to the CT and SPECT images to calculate the mean density values (D mean) and mean ventilation values (Vent mean), respectively. The final CT-derived ventilation images were generated by interpolation from the D mean values to yield . For the performance evaluation, the voxel- and region-wise differences between and SPECT were compared using Spearman's correlation and the Dice similarity coefficient index. Additionally, images were generated using two deformable image registration (DIR)-based methods, and , and compared with the SPECT images. Results: The correlation between the D mean and Vent mean of the super-voxel was 0.59 ± 0.09, representing a moderate-to-high correlation at the super-voxel level. In the voxel-wise evaluation, the method achieved a stronger average correlation (0.62 ± 0.10) with SPECT, which was significantly better than the correlations achieved with the (0.33 ± 0.14, p < 0.05) and (0.23 ± 0.11, p < 0.05) methods. For the region-wise evaluation, the Dice similarity coefficient of the high functional region for (0.63 ± 0.07) was significantly higher than the corresponding values for the (0.43 ± 0.08, p < 0.05) and (0.42 ± 0.05, p < 0.05) methods. Conclusion: The strong correlation between and SPECT demonstrates the potential usefulness of this novel method of ventilation estimation for surrogate ventilation imaging.

Trust-based distributed state estimation for microgrids with encoding-decoding mechanisms

In this article, a trust-based estimation algorithm in a distributed paradigm is developed for microgrids whose information transmission obeys the predetermined encoding and decoding rule. Because of weak communication protection, and harsh electromagnetic or geographical environments, the output of sensors in microgrids could be subject to outliers or cyberattacks, which will lead to anomalous estimates. According to such a challenge, a simple clustering method is employed to distinguish between trusted and untrusted data. In light of distinguished data, a novel distributed estimator under an encoding and decoding scheme is then proposed where the correction of untrusted data is executed by the cluster information. Furthermore, a performable algorithm is developed by optimizing the upper bound of error covariance and a novel decomposition of system matrices, and a condition is derived to check the boundedness of the developed iterative algorithm. In the end, a simulation example is given to verify the effectiveness.

Super pixels transmission map-based object detection using deep neural network in UAV video

ABSTRACT Object detection has become a very prominent subject for research in recent times. This study's main goal is to suggest a technique for video saliency object detection. It seems to sense that using the depth information in photos to detect salient things. Since depth offers abundant information about scene structure, object forms, and other 3D cues. This information is very compatible to distinguish between objects in the foreground and background. As a result of the high object density, small object size, and cluttered background, aerial photos and movies provide results with low precision. In this paper, the proposed SPTM (Super Pixel Transmission Map)-YOLO model, the input RGB image has applied Dark Channel Prior (DCP) method for estimating the transmission map. From the transmission map only, the background probability is estimated with the help of SLIC (simple linear iterative clustering algorithm) superpixel segmentation. That foreground extracted image is further learned with YOLO architecture to detect the objects effectively. For object detection in aerial images, this proposed SPTM-YOLO approach outperforms classic YOLO by up to 6% accuracy. Accurate detection of things that are small in size, partially occluded, and out of view is possible.

An Effective and Efficient Algorithm for K-Means Clustering With New Formulation

K-means is one of the most simple and popular clustering algorithms, which implemented as a standard clustering method in most of machine learning researches. The goal of K-means clustering is finding a set of cluster centers and minimizing the sum of squared distances between each sample and its nearest clustering center. In this paper, we proposed a novel K-means clustering algorithm, which reformulate the classical K-Means objective function as a trace maximization problem and then replace it with a new formulation. The proposed algorithm does not need to calculate the cluster centers in each iteration and requires fewer additional intermediate variables during the optimization process. In addition, we proposed an efficient iterative re-weighted algorithm to solve the involved optimization problem and provided the corresponding convergence analysis. The proposed algorithm keeps a consistent computational complexity as Lloyd's algorithm, <inline-formula><tex-math notation="LaTeX">$\mathcal {O}(ndk)$</tex-math></inline-formula> , but shows a faster convergence rate in experiments. Extensive experimental results on real world benchmark datasets show the effectiveness and efficiency of the proposed algorithm.

Complex Traffic Scene Image Classification Based on Sparse Optimization Boundary Semantics Deep Learning

With the rapid development of intelligent traffic information monitoring technology, accurate identification of vehicles, pedestrians and other objects on the road has become particularly important. Therefore, in order to improve the recognition and classification accuracy of image objects in complex traffic scenes, this paper proposes a segmentation method of semantic redefine segmentation using image boundary region. First, we use the SegNet semantic segmentation model to obtain the rough classification features of the vehicle road object, then use the simple linear iterative clustering (SLIC) algorithm to obtain the over segmented area of the image, which can determine the classification of each pixel in each super pixel area, and then optimize the target segmentation of the boundary and small areas in the vehicle road image. Finally, the edge recovery ability of condition random field (CRF) is used to refine the image boundary. The experimental results show that compared with FCN-8s and SegNet, the pixel accuracy of the proposed algorithm in this paper improves by 2.33% and 0.57%, respectively. And compared with Unet, the algorithm in this paper performs better when dealing with multi-target segmentation.

BGC: Belief gravitational clustering approach and its application in the counter-deception of belief functions

Counter-deception information fusion is a significant issue in Dempster–Shafer evidence theory (DST). How to effectively counter the deception is the key problem in belief function. Limited work has been presented, of which the negation view, degree of falsity view, and the minimum conflict view are popular ones. However, previous work may suffer from combinatorial explosion or be limited to simple practical application. Based on our previous belief universal gravitation (BUG) model, a simple belief gravitational clustering (BGC) is proposed to model the evidential clustering process. Some goals, like no parameter adjustment, no initial condition, objective and unique cluster number, and robustness are achieved. Furthermore, BGC-based fusion strategy is ulteriorly raised to determine whether the evidence should be fused, which fully considers the abnormal feature of the body of evidence and the nature of the combination rule to perceive the deception. Both theoretical analysis and experimental results demonstrate the accuracy and flexibility of the proposed work.

The Investigation of the Mixture Formation and Combustion Characteristic of the Spray-wall Impingement

In recent years, investigations into the formation of mixture or combustion characteristics of diesel spray-wall impingement have been summarized. On one hand, the air entrainment strength and fuel concentration distribution in the near-wall area during the spray-wall collision process have been studied. On the other hand, the combustion characteristics of the impinged spray, including ignition and combustion characteristics, have also been discussed. Additionally, the effect of impingement between spray and wall on real diesel engines’ operating condition has been analyzed and summarized. Results showed that increasing the pressure of the injection and shortening the collision distance could enhance the air entrainment strength of spray-wall impingement. Moreover, increasing the injection pressure, shortening the impingement distance, decreasing the environmental pressure, increasing the wall temperature, and reducing the nozzle diameter all improved the mixture formation. Conversely, reducing the environmental temperature, decreasing the nozzle diameter, and increasing the impingement distance all reduced the concentration of soot, and even achieved no soot formation. Under real diesel engine operation conditions, some of the soot formed in the spray-wall collision and deposited on the wall. The structure of these deposits was mainly a simple cluster structure composed of several basic particles, and the porous structure of the deposits was conducive to the oxidation of soot and reduced the deposition rate.

Comparing the Effects of Emotion Regulation Training and Mindfulness-based Cognitive Therapy on the Resilience and Self-compassion of Women With Irritable Bowel Syndrome

Background &amp; Aims The present study aims to compare the effects of emotion regulation training and mindfulness-based cognitive therapy (MBCT) on the resilience and self-compassion of women with irritable bowel syndrome (IBS). Materials &amp; Methods This is a quasi-experimental study with a pre-test/post-test/follow-up design. The study population consists of 300 women with IBS who visited the clinics of internal medicine physicians in Ilam, Iran, in 2018-2019. The sample size was determined 20 for each group based on the Fleiss method. Therefore, 60 were selected by a simple cluster sampling method and based on the entry criteria. They were divided into three groups of emotion regulation (n=20), MBCT (n=20), and control (n=20). After the interventions, the post-test and follow-up assessments were conducted for the groups. The instruments were the Connor-Davidson resilience scale and the self-compassion scale of Neff (2003). For data analysis, SPSS software, version 23 and repeated measures analysis of variance were used. Results Both emotion regulation training and MBCT had a significant effect on the resilience and self-compassion of women (P=0.001), where MBCT had a greater effect compared to emotional regulation training. Conclusion The MBCT can be used as an effective method to increase resilience and self-compassion of women with IBS.

Global survey of star clusters in the Milky Way

Aims. We built Galactic open star cluster mass functions (CMFs) for different age sub-samples and spatial locations in the wider solar neighbourhood. Here, we present a simple cluster formation and evolution model to reproduce the main features of the CMFs. Methods. We used an unbiased working sample of 2227 clusters of the Milky Way Star Cluster (MWSC) catalogue, which occupy the heliocentric cylinders with magnitude-dependent completeness radii of 1–5 kpc. The MWSC survey provides an extended set of open star cluster parameters, including tidal radii, distances, and ages. From an analytic three-component Galaxy model, we derived tidal masses of clusters with a typical accuracy of about 70%. Our simple model includes a two-section cluster initial mass function, constant cluster formation rate, supervirial phase after a sudden expulsion of the remaining gas, and cluster mass loss due to stellar evolution and the clusters’ gradual destruction in the Galactic tidal field. The dynamical evolution model is based on previous N-body simulations. Results. The obtained tidal masses have been added to the MWSC catalogue. A general CMF (GCMF), built for all cluster ages around the Sun, has a bell-like shape and extends over four decades in mass. The high-mass slope found for tidal mass log mt/M⊙ ≥ 2.3 is equal to 1.14 ± 0.07. The CMFs for different age groups show the same high-mass slopes, while the low-mass slope is nearly flat for the youngest sub-sample (clusters younger than 20 Myr) and about −0.7 for the others. The inner and outer sub-samples covering Galactocentric radii R = 4.2–8.1 kpc and 8.9–13.5 kpc, respectively, are consistent with the GCMF, once the exponential decline of the Galactic disc density is taken into account. The model suggests star formation with low efficiency of 15–20%, where only 10% of stars remain bound in a cluster after gas expulsion and subsequent violent relaxation. The cluster formation rate required to reproduce the observed distributions in age and mass is about 0.4 M⊙ pc−2 Gyr−1. Conclusions. The obtained high-mass slope of the GCMF for the wide neighbourhood of the Sun is similar to slopes determined earlier in nearby galaxies for more luminous clusters with log m/M⊙ &gt; 3.8. The MWSC catalogue supports models with a low star-formation efficiency, where 90% of stars are lost quickly after gas expulsion. The obtained cluster formation rate corresponds to open clusters’ contribution to the stellar content of the thin disc at the level of 30%.

Improved Initialization Method for Simple and Fast K-medoids Clustering

Initial solution selection is an important process in determining an optimal solution for the efficient classification of clustering methods in machine learning. This study proposes an improved initialization method for a simple and fast Kmedoids clustering algorithm, considering not only the sum of the relative distance rates for each data point, but also the distance between the previously selected medoids (representative objects). Selection of the balanced initial medoids causes the dissimilarity of patterns in the same cluster to be small and the dissimilarity of patterns in different clusters to be large. The performance of the proposed method is verified and validated based on two valid indices of clustering solutions by employing seven machine learning repository datasets of prominent applications with large improvements. The Mann–Whitney test is employed to assess the statistical significance of the performance differences between the method proposed by Park and Jun (2009) and the initialization method for clustering proposed here. The proposed initial selection method is effective, highly reliable, and computationally practical even for large problems.

Transforming graph data visualisations from 2D displays into augmented reality 3D space: A quantitative study

Modern video-based head-mounted displays allow users to operate along Milgram’s entire reality-virtuality continuum. This opens up the field for novel cross-reality applications that distribute data analytics tasks along this continuum to combine benefits of established 2D information visualisation in the real environment with immersive analytics. In this publication, we explore this potential by transforming 2D graph data from a planar, large-scale display in the real environment into a spherical layout in augmented reality 3D space, letting it appear as if the graph is moving out of the display. We focus on design aspects of this transformation that potentially help users to form a joint mental model of both visualisations and to continue their tasks seamlessly in augmented reality. For this purpose, we implemented a framework of transformation parameters that can be categorised as follows: transformation methods, node transformation order (groupings) and different ways of visual interconnection. Variants in each of these areas were investigated in three quantitative user studies in which users had to solve a simple cluster search task. We confirmed that a visual transformation from 2D to 3D helps users to continue their tasks in augmented reality with less interruptions, and that node transformation order should be adjusted to data and task context. We further identified that users can perform tasks more efficiently when a user-controlled transformation is used, while a constant transformation with fixed duration can contribute to lower error rates.

Zero watermarking scheme for privacy protection in e-Health care

E-health care is an emerging field where health services and information are delivered and offered over the Internet. So the health information of the patients communicated over the Internet has to protect the privacy of the patients. The patient information is embedded into the health record and communicated online which also induces degradation to the original information. So, in this article, a zero watermarking scheme for privacy protection is proposed which protects the privacy and also eliminates the degradation done during embedding of patient information into the health record. This method is based on simple linear iterative clustering (SLIC) superpixels and partial pivoting lower triangular upper triangular (PPLU) factorization. The novelty of this article is that the use of SLIC superpixels and PPLU decomposition for the privacy protection of medical images (MI). The original image is subjected to SLIC segmentation and non-overlapping high entropy blocks are selected. On the selected blocks discrete wavelet transform (DWT) is applied and those blocks undergo PPLU factorization to get three matrices, L, U and P, which are lower triangular, upper triangular and permutation matrix respectively. The product matrix is used to construct a zero-watermark. The technique has been experimented on the UCID, BOWS and SIPI databases. The test results demonstrate that this work shows high robustness which is measured using normalized correlation (NC) and bit error rate (BER) against the listed attacks.