Abbas Fadhil Hamzah Alharan

Histogram Equalization (HE) is a dominant contrast enhancement method mainly used in image processing expanse due to its efficacy in forming images with good contrast. Various versions of works' efforts in Global HE have been created over the years. Improperly, these methods’ resilience to distortion remains questionable. This paper proposes to evaluate the selected two objective metrics which are the Absolute Mean Brightness Error (AMBE) and Entropy used for evaluation of image quality assessment algorithms (IQAs) based onGHE techniques. A review for thesetwo objective metrics is made. It is found that the two IQAs fail to detect the occurrence of noise artifacts and gray level brightness saturation effectively.Also,an experiment was conducted by using subjective evaluation to assess the performance of these twoobjective metrics. The statistical results of the experimentreveal that they have poor correlation with Human Visual Perception (HVP) of distortions.

Popular Decision Tree Algorithms of Data Mining Techniques: A Review

This book highlights a new hybrid technique that is dependent on artificial bee colony (ABC) and k-means algorithms to retrieve the most similar image to the image query. ABC algorithm guaranty an optimized clustering for the contents (Color and Texture: extracted using common methods) of images. The new technique is applied on set of images (Wang dataset), where it showed high positive result in term of retrieval precision.

In this paper, a new clustering method is proposed for CBIR system; this method depends on combining ABC and k-means algorithm. Four features are used with the proposed method to retrieve the images. These features are extracted by: color histogram of HSV image and color histogram of opponent image to describe the color, Gabor filters and Ranklet transform for RGB image to describe the texture. The proposed hybrid clustering method is a clustering process for database of each feature using k-means algorithm enhanced by ABC algorithm. The innovation in this approach is that each solution in ABC algorithm represents the centroids of clusters that come out from applying k-means algorithm. The proposed method is applied on Wang dataset (1000 images in 10 classes) and evaluated by comparing the test results of the proposed scheme with another existing method uses same database. The results proved that the proposed method is superior to the existing method in terms of the precision in 6 out of 10 categories of WANG dataset, such that the average of the precisions for all categories is 0.8093.

Due to the diversity of data from multiple sources, centralized Complex Event Processing (CEP) systems have become ineffective in event detection involving large amounts of data. These data need to be processed quickly across multiple nodes. Traditionally, CEP systems such as Esper lack horizontal scalability and fault-tolerance features. To overcome these limitations, Esper has been integrated with Storm, which is a scalable, fault-tolerant, distributed system. In this paper, firstly, we have integrated Storm with Es per to cope with high volumes of events continuously generated from multiple sources. Secondly, we have developed a tool in Java that reads a description of computation and generates a Maven project of the integrated system. Finally, the integrated system has been deployed on multiple nodes and tested successfully with real-time data analytics. The experimental results have demonstrated the ability of the system in terms of a steady increase in throughput by adding more nodes.

You can download Visual studio 2010 from the following direct link https://drive.google.com/file/d/1ItjjRBOxPuWhUQ5lkM7P1qwXI48L5qWT/view?usp=share_link