ZG Abdulrazaq, MR Younus, Nasaq, 2023

    Semantic segmentation is effective in numerous object classification tasks such as autonomous vehicles and scene understanding. With the advent in the deep learning domain, lots of efforts are seen in applying deep learning algorithms for semantic segmentation. Most of the algorithms gain the required accuracy while compromising on their storage and computational requirements. The work showcases the implementation of Convolutional Neural Network (CNN) using Discrete Cosine Transform (DCT), where DCT exhibit exceptional energy compaction properties. The proposed Adaptive Weight Wiener Filter (AWWF) rearranges the DCT coefficients by truncating the high frequency coefficients. AWWF-DCT model reinstate the convolutional l

In information security, fingerprint verification is one of the most common recent approaches for verifying human identity through a distinctive pattern. The verification process works by comparing a pair of fingerprint templates and identifying the similarity/matching among them. Several research studies have utilized different techniques for the matching process such as fuzzy vault and image filtering approaches. Yet, these approaches are still suffering from the imprecise articulation of the biometrics’ interesting patterns. The emergence of deep learning architectures such as the Convolutional Neural Network (CNN) has been extensively used for image processing and object detection tasks and showed an outstanding performance compare

Directional Compact Geographic Forwarding (DCGF) routing protocol promises a minimal overhead generation by utilizing a smart antenna and Quality of Service (QoS) aware aggregation. However, DCGF was tested only in the attack-free scenario without involving the security elements. Therefore, an investigation was conducted to examine the routing protocol algorithm whether it is secure against attack-based networks in the presence of Denial-of-Service (DoS) attack. This analysis on DoS attack was carried out using a single optimal attacker, A1, to investigate the impact of DoS attack on DCGF in a communication link. The study showed that DCGF does not perform efficiently in terms of packet delivery ratio and energy consumption even on a sin

Linguistic studies present a distinguished place among modern human studies, as we find this clear in the scientific research institutions of the developed nations, it is the main pillar in the strengthening of links and consolidation pillars between individuals and groups. It is a language and between people's thoughts, feelings and actions, and has been able to show that language is not only a tool of expression but is closely linked to the intellectual, emotional and social life of these people individuals and groups.
    The derivation is a major step in Arabic in classifying formulas into weights with special morphological values; these are of great importance in sentences and structures that are the domain of the searc

The security of message information has drawn more attention nowadays, so; cryptography has been used extensively. This research aims to generate secured cipher keys from retina information to increase the level of security. The proposed technique utilizes cryptography based on retina information. The main contribution is the original procedure used to generate three types of keys in one system from the retina vessel's end position and improve the technique of three systems, each with one key. The distances between the center of the diagonals of the retina image and the retina vessel's end (diagonal center-end (DCE)) represent the first key. The distances between the center of the radius of the retina and the retina vessel's end (ra

The background subtraction is a leading technique adopted for detecting the moving objects in video surveillance systems. Various background subtraction models have been applied to tackle different challenges in many surveillance environments. In this paper, we propose a model of pixel-based color-histogram and Fuzzy C-means (FCM) to obtain the background model using cosine similarity (CS) to measure the closeness between the current pixel and the background model and eventually determine the background and foreground pixel according to a tuned threshold. The performance of this model is benchmarked on CDnet2014 dynamic scenes dataset using statistical metrics. The results show a better performance against the state-of the art