A new block-based method for copy move forgery detection under image geometric transforms

Copy move forgery detection (CMFD) is one of the most active subtopic in forgery scheme. The methods of CMFD are divided into to block-based method and keypoint-based method in general. Compared with keypoint-based method, block-based method can detect undetectable detail without morphology segmentation. But many block-based methods detect the plain copy-move forgeries only. They have been incompetent to detect the post-processing operations such as various geometrical distortions, and then fail to detect the forgery regions accurately. Therefore, this paper presents an improved block-based efficient method for CMFD. Firstly, after pre-processing, an auxiliary overlapped circular block is presented to divide the forged image into overlapped circular blocks. The local and inner image feature is extracted by the Discrete Radial Harmonic Fourier Moments (DRHFMs) with the overlapped circular block from the suspicious image. Then, the similar feature vectors of blocks are searched by 2 Nearest Neighbors (2NN) test. Euclidean distance and correlation coefficient is employed to filter these features and then remove the false matches. Morphologic operation is employed to delete the isolated pixels. A series of experiments are done to analyze the performance for CMFD. Experimental results show that the new DRHFMs can obtain outstanding performance even under image geometrical distortions.     

Accelerated Manhattan hashing via bit-remapping with location information

Multimedia Tools and Applications - Hashing is a binary-code encoding method which tries to preserve the neighborhood structures in the original feature space, in order to realize efficient...     

Visual topic discovering,tracking and summarization from social media streams

Multimedia Tools and Applications - Nowadays, microblogging has become popular, with hundreds of millions of short messages being posted and shared every minute on a variety of topics in social...     

High-fidelity lossless data hiding based on predictors selection

Multimedia Tools and Applications - Reversible data hiding based on prediction methods is a data hiding technique wherein secret bits can be efficiently hidden into cover images. In this paper, we...     

Highly non-rigid video object tracking using segment-based object candidates

Multimedia Tools and Applications - A novel scheme for non-rigid video object tracking using segment-based object candidates is proposed in this paper. Rather than using a conventional bounding...     

Fraud detection using fraud triangle risk factors

The objective of this study is to identify the financial statement fraud factors and rank the relative importance. First, this study reviews the previous studies to identify the possible fraud indicators. Expert questionnaires are distributed next. After questionnaires are collected, Lawshe’s approach is employed to eliminate these factors whose CVR (content validity ratio) values do not meet the criteria. Further, the remaining 32 factors are reviewed by experts to be the measurements suitable for the assessment of fraud detection. The Analytic Hierarchy Process (AHP) is utilized to determine the relative weights of the individual items. The result of AHP shows that the most important dimension is Pressure/Incentive and the least one is Attitude/rationalization. In addition, the top five important measurements are “Poor performance”, “The need for external financing”, “Financial distress”, “Insufficient board oversight”, and “Competition or market saturation”. The result provides a significant advantage to auditors and managers in enhancing the efficiency of fraud detection and critical evaluation.     

Competition in wearable device market: the effect of network externality and product compatibility

The rapid growth in consumer adoption of wearable devices has garnered the attention of both practitioners and academia. Competition in the wearable device market is both substantial and complicated. In this study, we investigate the impact of network externality on wearable device competition in a two-dimensional product differentiation model. We consider a market that has a broad array of products (horizontal differentiation) and various quality levels (vertical differentiation). We study two types of network externalities according to the product compatibility in two types of market structures. Our model indicates that firm profits are decreased by network externalities in horizontal dominance. Network externality also increases (decreases) the higher-quality (lower-quality) firm’s profit in vertical dominance. Moreover, firms should ensure that their products are incompatible with those of rivals when network externality is large, and they should release compatible products when network externality is small in horizontal dominance. Firms should always ensure that their products are compatible with those of competitors in vertical dominance.     

Nonlinear dynamic responses of electrostatically actuated microcantilevers containing internal fluid flow

A nonlinear theoretical model for electrostatically actuated microcantilevers containing internal fluid flow is developed in the present study, which takes into account the geometric and electrostatic nonlinearities. A four-degree-of-freedom and eight-dimensional analytical modeling is presented for investigating the stability mechanism and nonlinear dynamic responses near and away from the instability boundaries of the fluid-loaded cantilevered microbeam system. Firstly, the reliability of the theoretical model is examined by comparing the present results with previous experimental and numerical results. It is found that, with the increase in flow velocity, flutter instability, pull-in instability and the combination of both can occur in this dynamical system. It is also found that the instability boundary depends on the initial conditions significantly when the internal fluid is at low flow rate. Nextly, the phase portraits and time histories of the microbeam’s oscillations and bifurcation diagrams are established to show the existence of periodic, chaotic divergence and transient periodic-like motions.     

基于概率的无监督缺陷预测方法

软件缺陷预测能够提高软件开发和测试的效率,保障软件质量。无监督缺陷预测方法具有不需要标签数据的特点,从而能够快速应用于工程实践中。提出了基于概率的无监督缺陷预测方法—PCLA,将度量元值与阈值的差值映射为概率,使用概率评估类存在缺陷的可能性,然后再通过聚类和标记来完成缺陷预测,以解决现有无监督方法直接根据阈值判断时对阈值比较敏感而引起的信息丢失问题。将PCLA方法应用在NetGen和Relink两组数据集,共7个软件项目上,实验结果表明PCLA方法在查全率、查准率、F-measure上相对现有无监督方法分别平均提升4.1%、2.52%、3.14%。     

Use of a Modified UTAUT Model to Investigate the Perspectives of Internet Access Device Users

This study integrates perceived enjoyment and cyberloafing with the unified theory of acceptance and use of technology (UTAUT) and uses a modified UTAUT model to investigate the behavioral intention and user behavior of access internet device users. The research results show that perceived enjoyment can be used as the antecedence variable of performance expectancy (PE) and effort expectancy (EE). In addition, PE, EE, and social influence will all lead to the occurrence of cyberloafing behavior and increased internet browsing time; however, the hypothesis of the moderator is not fully supported. The results can be provided as reference for subsequent researchers to re-modify the model.