Recently, users and news followers across websites face many fabricated images. Moreover, it goes far beyond that to the point of defaming or imprisoning a person. Hence, image authentication has... Show More

Recently, users and news followers across websites face many fabricated images. Moreover, it goes far beyond that to the point of defaming or imprisoning a person. Hence, image authentication has become a significant issue. One of the most common tampering techniques is copy-move. Keypoint-based methods are considered as an effective method for detecting copy-move forgeries. In such methods, the feature extraction process is followed by applying a clustering technique to group spatially close keypoints. Most clustering techniques highly depend on the existence of a specific threshold to terminate the clustering. Determination of the most suitable threshold requires a huge amount of experiments. In this article, a copy-move forgery detection method is proposed. The proposed method is based on automatic estimation of the clustering threshold. The cutoff threshold of hierarchical clustering is estimated automatically based on clustering evaluation measures. Experimental results tested on various datasets show that the proposed method outperforms other relevant state-of-the-art methods.

This article presents a robust 3D mesh watermarking approach, which adopts an optimization method of selecting watermark vertices for 3D mesh models. The proposed approach can enhance the... Show More

This article presents a robust 3D mesh watermarking approach, which adopts an optimization method of selecting watermark vertices for 3D mesh models. The proposed approach can enhance the imperceptibility of the watermarked model without affecting the robustness and capacity factors. The proposed watermark approach depends on an embedding algorithm that use a clustering strategy, based on K−means clustering algorithm in conjunction with the particle swarm optimization to divide the mesh model vertices into groups. Points of interest set (POIs) are selected from these clustered groups and mark it as watermark vertices where the (POIs) are invariant to most of the geometrical and connectivity attacks. Then, the proposed approach inserts the watermark bit stream in the decimal part of spherical coordinates for these selected watermark vertices. The experimental results confirm that the proposed approach proves its superiority compared with state-of-the-art techniques with respect to imperceptibility and robustness.

The immense crime rates resulting from using pistols have led governments to seek solutions to deal with such terrorist incidents. These incidents have a negative impact on public security and cause... Show More

The immense crime rates resulting from using pistols have led governments to seek solutions to deal with such terrorist incidents. These incidents have a negative impact on public security and cause panic among citizens. From this point, facing a pandemic of weapon violence has become an important research topic. One way to reduce this kind of violence is to prevent it via remote detection and to give an appropriate response in a short time. Video surveillance is the process of monitoring the behavior of people and objects. Surveillance systems can be employed in security applications as legal evidence. Moreover, it is used widely in suspicious activity detection applications. Intelligent video surveillance systems (IVSSs) are the use of automatic video analytics to enhance the effectiveness of traditional surveillance systems. With the rapid development in Deep Learning (DL), it is now widely used to address the problems existing in traditional detection techniques. In this article, an approach to detect pistols and guns in video surveillance systems is proposed. The presented approach does not need any invasive tools in the weapon detection process. It uses DL in the classification and the detection processes. The proposed approach enhances the obtained results by applying Transfer Learning (TL). It employs two different DL techniques: AlexNet and GoogLeNet. Experimental results verify the adaptability of detecting different types of pistols and guns. The experiments were conducted on a benchmark gun database called Internet Movie Firearms Database (IMFDB). The results obtained suggest that the proposed approach is promising and outperforms its counterparts.

In the present study, a multimodal biometric authentication method is presented to confirm the identity of a person based on his face and iris features. This method depends on multiple biometric... Show More

In the present study, a multimodal biometric authentication method is presented to confirm the identity of a person based on his face and iris features. This method depends on multiple biometric techniques that combine face and iris (left and right) features to recognize. The authors have designed and applied a system to identify people. It depends on extracting the features of the face using Rectangle Histogram of Oriented Gradient (R-HOG). The study applies a feature-level fusion using a novel fusion method which employs both the canonical correlation process and the proposed serial concatenation. A deep belief network was used for the recognition process. The performance of the proposed systems was validated and evaluated through a set of experiments on SDUMLA-HMT database. The results were compared with others, and have shown that the fusion time has been reduced by about 34.5%. The proposed system has also succeeded in achieving a lower equal error rate (EER), and a recognition accuracy up to 99%.

Big Data management is trending research that seeks to find a framework that will give support to decision makers in governments and enterprises organizations. For the rapid growth of data, dealing... Show More

Big Data management is trending research that seeks to find a framework that will give support to decision makers in governments and enterprises organizations. For the rapid growth of data, dealing with Big Data with respect to management and finding new values has drawn attention recently. Strategies should be established together with the goals, vision, and objectives of an organization to manage Big Data. Big data management frameworks are the main components for the implementation of Big Data service. Many organizations that deals with Big Data have three critical problems, how to manage Big Data, how can Big Data create new values reference to its strategies and business needs, and how it can take the correct decision in the correct time. In this article, the authors propose a Big Data management framework that will handle all Big Data operation beginning with collecting data until making analysis and how new value can be created. The proposed framework also takes care of other factors such as organization strategies, governance, and security.

Most frequent itemset mining algorithms (FIMA) discover hidden relationships from unrelated items. They find the most frequent itemsets depending only on the frequency of the item's existence in the... Show More

Most frequent itemset mining algorithms (FIMA) discover hidden relationships from unrelated items. They find the most frequent itemsets depending only on the frequency of the item's existence in the dataset. These algorithms give all items the same importance, and neglect the differences in importance of the items. They assume the full certainty of data, but in most cases, real word data may be uncertain. As a result, the data could be incomplete and/or imprecise. These two problems are the most common challenges that face FIMA algorithms. Some new algorithms proposed some solutions to face these two issues separately. In other words, some algorithms handle item importance only, and others handle uncertainty only. Few algorithms dealt with the two issues together. In this article, the single scan for weighted itemsets over the uncertain database (SSU-Wfim) is proposed. It depends on the single scan frequent itemsets algorithm (SS_FIM), and enhances it to deal with weighted items in an uncertain database. SSU_WFIM deals with the uncertainty of data by giving each item in a transaction an additional value to indicate occurrence likelihood. It gives the items different values to define the weight of them. It uses a table called Ptable to save the items and their probability values. This table is used to generate all possible candidates itemsets. The results indicate the high performance in aspects of runtime, memory consumption and scalability of SSU-Wfim comparing with the UApriori algorithm. The proposed algorithm saves time and memory with a percentage exceeds 70% for all tested datasets.