Papers by Mohammed Alonazi
IEEE Access
With the latest advancements, hand gesture recognition is becoming an effective way of communicat... more With the latest advancements, hand gesture recognition is becoming an effective way of communication and gaining popularity from a research point of view. Hearing impaired people around the world need assistance, while sign language is only understood by a few people around the globe. It becomes challenging for untrained people to communicate easily, research community has tried to train systems with a variety of models to facilitate communication with hearing impaired people and also human-computer interaction. Researchers have detected gestures with numerous recognition rates; however, the recognition rate still needs improvement. As the images captured via cameras possess multiple issues, the light intensity variation makes it a challenging task to extract gestures from such images, extra information in captured images, such as noise hinders the computation time, and complex backgrounds make the extraction of gestures difficult. A novel approach is proposed in this paper for character detection and recognition. The proposed system is divided into five steps for hand gesture recognition. Firstly, images are pre-processed to reduce noise and intensity is adjusted. The pre-processed images region of interest is detected via directional images. After hand extraction, landmarks are extracted via a convex hull. Each gesture is used to extract geometric features for the proposed hand gesture recognition (HGR) system. The extracted features helped in gesture detection and recognition via the Convolutional Neural Network (CNN) classifier. The proposed approach experimentation result demonstrated over the MNIST dataset achieved a gesture recognition rate of 93.2% and 90.2% with one-third and two-third training validation systems, respectively. Also, the proposed system performance is validated on the ASL dataset, giving accuracy of 91.6% and 88.14% with one-third and twothird training validation systems, respectively. The proposed system is also compared with other conventional systems. Different emerging domains such as human-computer interaction (HCI), human-robot interaction (HRI), and virtual reality (VR) are applicable to the proposed system to fill the communication gap. INDEX TERMS ASL sign language, character understanding, landmark identification, geometric feature, hand gesture recognition, CNN. The associate editor coordinating the review of this manuscript and approving it for publication was Parikshit Sahatiya.
IEEE Access
Gesture recognition in dynamic images is challenging in computer vision, automation and medical f... more Gesture recognition in dynamic images is challenging in computer vision, automation and medical field. Hand gesture tracking and recognition between both human and computer must have symmetry in real world. With advances in sensor technology, numerous researchers have recently proposed RGB gesture recognition techniques. In our research paper, we introduce a reliable hand gesture tracking and recognition model that is accurate despite any complex environment, it can track and recognise RGB dynamic gestures. Firstly, videos are converted into frames. After images light intensity adjustment and noise removal, images are passed through CNN for hand gesture extraction. Then from the extracted hand, features are extracted from full hand. Neural gas and locomotion thermal mapping are extracted to make the feature vector. The feature vector are then passed through the fuzzy optimiser to reduce the uncertainties and the fuzziness. The optimised features are then passed to the classifier Deep Belief Network (DBW) for the classification of the gestures. Egogesture and Jester datasets are used for the validation of proposed systems. The experimental results over Egogesture and Jester datasets demonstrate overall accuracies of 90.73% and 89.33% respectively. The experiments proves our system readability and suitability of our proposed model with the other state of the arts model. INDEX TERMS Convolution neural network, neural gas, thermal locomotion mapping, fuzzy logic, deep belief network, hand detection and tracking.
IEEE Access
The advancement of computer vision technology has led to the development of sophisticated algorit... more The advancement of computer vision technology has led to the development of sophisticated algorithms capable of accurately recognizing human actions from red-green-blue videos recorded by drone cameras. Hence, possessing an exceptional potential, human action recognition also faces many challenges including, tendency of humans to perform the same action in different ways, limited camera angles, and field of view. In this research article, a system has been proposed to tackle the forementioned challenges by using red-green-blue videos as input while the videos were recorded by drone cameras. First of all, the video was split into its constituent frames and then gamma correction was applied on each frame to obtain an optimized version of the image. Then the Felzenszwalb's algorithm performed the segmentation to segment out human from the input image and human silhouette was generated. Utilizing the silhouette, skeleton was extracted to spot thirteen body key points. The key points were then used to perform elliptical modeling to estimate the individual boundaries of the body parts while the elliptical modeling was governed by the Gaussian mixture model-expectation maximization algorithm. The elliptical models of the body parts were utilized to spot fiducial points that if tracked, could provide very useful information about the performed action. Some other features that were extracted for this study include, the 3d point cloud feature vector, relative distance and velocity of the key-points, and their mutual angles. The features were then forwarded for optimization under a quadratic discriminant analysis and finally, a convolutional neural network was trained to perform the action classification. Three benchmark datasets including, the Drone-Action dataset, the UAV-Human dataset, and the Okutama-Action dataset were used for a comprehensive experimentation. The system outperformed the state-of-the-art approaches by securing accuracies of 80.03%, 48.60%, and 78.01% over the Drone-Action dataset, the UAV-Human dataset, and the Okutama-Action dataset respectively.
Computer Systems Science and Engineering
Human-Computer Interaction (HCI) is a sub-area within computer science focused on the study of th... more Human-Computer Interaction (HCI) is a sub-area within computer science focused on the study of the communication between people (users) and computers and the evaluation, implementation, and design of user interfaces for computer systems. HCI has accomplished effective incorporation of the human factors and software engineering of computing systems through the methods and concepts of cognitive science. Usability is an aspect of HCI dedicated to guaranteeing that human-computer communication is, amongst other things, efficient, effective, and sustaining for the user. Simultaneously, Human activity recognition (HAR) aim is to identify actions from a sequence of observations on the activities of subjects and the environmental conditions. The vision-based HAR study is the basis of several applications involving health care, HCI, and video surveillance. This article develops a Fire Hawk Optimizer with Deep Learning Enabled Activity Recognition (FHODL-AR) on HCI driven usability. In the presented FHODL-AR technique, the input images are investigated for the identification of different human activities. For feature extraction, a modified SqueezeNet model is introduced by the inclusion of few bypass connections to the SqueezeNet among Fire modules. Besides, the FHO algorithm is utilized as a hyperparameter optimization algorithm, which in turn boosts the classification performance. To detect and categorize different kinds of activities, probabilistic neural network (PNN) classifier is applied. The experimental validation of the FHODL-AR technique is tested using benchmark datasets, and the outcomes reported the improvements of the FHODL-AR technique over other recent approaches.
IEEE Access
Autonomous vehicle detection and tracking are crucial for intelligent transportation management a... more Autonomous vehicle detection and tracking are crucial for intelligent transportation management and control systems. Although many techniques are used to develop smart traffic systems, this article discusses vehicle detection and tracking using pixel-labeling and real-time tracking. We propose a novel smart traffic control system that segments the image using an Extreme Gradient Boost (XGBoost) classifier to extract the foreground objects. The proposed model is divided into the following steps: 1) at first, all the images are preprocessed to remove noise; 2) pixel-labeling is performed by using the XGBoost classifier to separate the background from the foreground; 3) all the pixels classified as a vehicle was extracted and converted into a binary image, then blob extraction technique is used to localize each vehicle; 4) to verify the detected vehicles Intersection over Union (IoU) score using the ground truth is calculated; 5) all verified vehicles were subjected to Visual Geometry Group (VGG) feature extraction and based on which a unique identifier was assigned to each of them to enable multi-object tracking across the image frames; 6) vehicles are counted and categorized into stationary and moving cars by detecting motion in each of them using Farneback optical flow algorithm; and 7) finally, the Simple Online and Real-time Tracker (SORT) is used for tracking. The proposed model outperforms existing state-of-the-art traffic monitoring techniques in terms of precision, achieving 0.86 for detection and 0.92 for tracking with the Karlsruher Institut for Technology Aerial Image Sequences (KIT-AIS) dataset, 0.83 for detection, and 0.87 for tracking with the Vision Meets Drone Single Object-Tracking (VisDrone) dataset. The proposed system can be used for several purposes, such as vehicle identification in traffic, traffic density detection at intersections, traffic flow conditions on the road, and providing a pedestrian way.
This paper presents a proposal for a mobile government<br> adoption and utilization model (... more This paper presents a proposal for a mobile government<br> adoption and utilization model (MGAUM), which is a framework<br> designed to increase the adoption rate of m-government services<br> in Saudi Arabia. Recent advances in mobile technologies such are<br> Mobile compatibilities, The development of wireless communication,<br> mobile applications and devices are enabling governments to<br> deliver services in new ways to citizens more efficiently and<br> economically. In the last decade, many governments around the<br> globe are utilizing these advances effectively to develop their next<br> generation of e-government services. However, a low adoption rate of<br> m-government services by citizens is a common problem in Arabian<br> countries, including Saudi Arabia. Yet, to our knowledge, very little<br> research has been conducted focused on understanding the factors<br> that influence citizen adoption o...
2019 Federated Conference on Computer Science and Information Systems (FedCSIS), 2019
Many governments worldwide are taking advantage of the latest developments in mobile technology t... more Many governments worldwide are taking advantage of the latest developments in mobile technology to take the digital delivery of government information and services (e-government) to their citizens a stage further. Accessing government information and services via a mobile device is known as m-government, a system designed to serve citizens, companies and government agencies alike. M-government also has unique advantages over e-government, not least enabling users to access government services at any time and from any location. This paper presents a pilot study of the MGAUM model that was developed to analyze factors influencing the adoption rate of m-government services in Saudi Arabia. With the aim of validating a survey instrument with which to conduct the main study in Saudi Arabia, a pilot survey instrument was developed and modified by using previous instruments from research into both e-government and m-government. This pilot questionnaire was distributed to 71 Saudi citizens ...
2019 Federated Conference on Computer Science and Information Systems (FedCSIS), 2019
The government of Saudi Arabia has adopted MGovernment for the effective delivery of services. On... more The government of Saudi Arabia has adopted MGovernment for the effective delivery of services. One advantage that it offers is unique opportunities for real-time and personalized access to government information and services. However, a low adoption rate of m-Government services by citizens is a common problem in Arab countries, including Saudi Arabia, despite the best efforts of the Saudi government. Therefore, this paper explores the determinants of citizens’ intention to adopt and use m-Government services, in order to increase the adoption rate. This study was based on the Mobile Government Adoption and Utilization Model (MGAUM) that was developed for the purpose. Data was collected, and the final sample consisted of 1,286 valid responses. The descriptive analysis presented in this paper indicates that all the proposed factors in our MGAUM model were statistically significant in influencing citizens’ intention to adopt and use m-Government services.
MGAUM: a new framework for the mobile government service adoption in Saudi Arabia
Many governments are now taking advantage of the latest developments in mobile technology to take... more Many governments are now taking advantage of the latest developments in mobile technology to take the digital delivery of government information and services (e-government) to their citizens, companies and other government agencies a stage further. Accessing government information and services via a mobile device (m-government) also has unique advantages over e-government, not least enabling users to access government services at any time and from any location. Nevertheless, many Arab countries including Saudi Arabia, are experiencing a low adoption rate of these services, and face a number of issues related to adoption, implementation and use. In spite of this, a review of the literature shows that little research into identifying and understanding the factors that influence adoption of m-government services by citizens from citizens’ and providers’ perspectives in these countries has been conducted. Thus, this research aims to investigate and analyze factors that can impact Saudi ...
Perceptions Towards the Adoption and Utilization of M-Government Services: A Study from the Citizens' Perspective in Saudi Arabia
The government of Saudi Arabia has adopted M-Government for the effective delivery of services. O... more The government of Saudi Arabia has adopted M-Government for the effective delivery of services. One advantage of adding the M-Government channel to government services is that it offers unique opportunities for real-time and personalized access to government information and services through the advantage of wireless technology. However, a low adoption rate of M-Government services by citizens is a common problem in Arabian countries, including Saudi Arabia, despite the best efforts of the Saudi government. Therefore, this paper explores the determinants of citizens’ intention to adopt and use M-Government services, in order to increase the adoption rate. This study was based on the Mobile Government Adoption and Utilization Model (MGAUM) that was developed to improve adoption. Data was collected from 1,882 Saudi citizens, and the final sample consisted of 1,286 valid responses. The result of the descriptive analysis presented in this paper indicates that all the proposed factors in ...
Uploads
Papers by Mohammed Alonazi