2019 2nd International Conference on new Trends in Computing Sciences (ICTCS)
Stand along single board computers (SoC) have become so inexpensive and yet so powerful that pave... more Stand along single board computers (SoC) have become so inexpensive and yet so powerful that paved the way for easily developing fully automated systems. SoC systems are equipped with sensors, cameras and various embedded systems that allow developing systems that interact with the surrounding environment. Therefore, the task of capturing images of License plates and using Optical Character Recognition (OCR) techniques to recognize the numerals and characters allows for developing an inexpensive License Plate (LP) Recognition system. LP systems are important and can be used for various application from traffic control, toll payment, and parking access. This paper proposes a Raspberry PI based LP recognition for Arabic/English Characters and Numeral on license plates used in Saudi Arabia. The proposed process utilizes the phases of Preprocessing, Segmentation, Feature Extraction and Classification. At the end of the preprocessing phase, the Characters and Numerals are segmented. Pixel distribution and Horizontal projection profiles are used in the feature extraction phase for the segmented image. Distance Classifier and k-nearest neighbors classifier are used in the classification phase. The proposed system achieved an accuracy of 90.6%. The advantage of such a system is the low cost and portability making it affordable and easily deployable in any location.
2020 IEEE 9th International Conference on Communication Systems and Network Technologies (CSNT)
Computer Vision coupled with Positioning Systems Technology has contributed significantly in assi... more Computer Vision coupled with Positioning Systems Technology has contributed significantly in assisting visually impaired people to independently perform their daily routine tasks. This paper proposes COMPASS, an Indoor Positioning System (IPS) based solution for visually impaired students to move around the university campus independently. COMPASS is a navigation system for the visually impaired students at PMU that consists of three important components which are: an android application running on a smartphone, smart bracelet, and smart shoes. The android application is used to upload student’s class schedule to help them navigate (through Bluetooth based beacons) to and from classes and around the campus. Also, it allows them to call university administrators by simply clicking on a button embedded in the mobile app. The Raspberry Pi based smart bracelet serves as a verification tool (using Tesseract enabled image detection) to ensure that the student arrives at the right class at the right time. As for the smart shoes, it ensures the safety of the student while walking around the campus by detecting obstacles (using ultrasonic sensors) along the way. COMPASS has been extensively tested in a university environment for navigating visually impaired students. COMPASS is economical, small-sized, accurate and uses open source software tools. It can be potentially used for both educational and commercial applications.
2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), 2018
In the digital age, developing an automated system to convert old printed books into digital form... more In the digital age, developing an automated system to convert old printed books into digital form is a challenging task. In this paper we propose a novel technique for the recognition of Arabic scanned documents both with normal and complex layouts. The proposed algorithm is based on the local adaptive thresholding and geometric features which according to the author’s knowledge is the first time it is applied to Arabic document image recognition based on the Physical Layout Analysis (PLA). The proposed method was applied to dataset consisting of 90 images collected from 700 books from various publishers and contains a total of 1112 zones; text zone, image zone, and graphic zone. The proposed algorithm achieved promising results with overall average recognition of 86.71% for Text and Image block regions for all three sets. The proposed novel algorithm outperforms the techniques mentioned in previous literature.
Deferent types of assessment are used to measure the achievements of the Student Learning Outcome... more Deferent types of assessment are used to measure the achievements of the Student Learning Outcomes (SOs) and the Course LearningOutcomes (COs) like direct, indirect, quantitative and qualitative. It is powerful to have a good approach to report the data and automated system for evaluatingthe performance indicators used in the outcomesmeasurement.Since the Student Outcomes are unmeasurable, group of measurable Key Performance Indicators (KPI) are extracted from each SO.In this paper, we propose a new comprehensive combinational approach which utilizes the assessment of the COs and SOs.The combination approach includes Threshold, Average, and Performance Vector used to assess the achievement of the course outcomes. And the KPIs used to measure the achievement of the SO. KeywordsABET; Assessment tool;Student Outcomes; Course Learning Outcomes; Key Performance Indicators.
Data Structure is an important and compulsory course in the computer science and engineering. The... more Data Structure is an important and compulsory course in the computer science and engineering. The topics of the course require detailed view for various algorithms such as queues, stacks, sort, search, trees and graphs. Due to the complexity of teaching and understanding of this course, we are focusing in measuring the student performance and the course learning outcomes. This paper describes methodology for providing a quantitative measurement of data structure course. The methodology uses a combination of three approaches (average, threshold, and performance vector) to assess course learning outcomes. The method utilizes data obtained from students’ marks in exams, tests, projects, and other formal assessments. A computerized system has been developed based on this method to expedite the analysis process.
Journal of Telecommunication, Electronic and Computer Engineering, 2017
With the advances in machine learning techniques, handwritten recognition systems also gained imp... more With the advances in machine learning techniques, handwritten recognition systems also gained importance. Though digit recognition techniques have been established for online handwritten numerals, an optimized technique that is writer independent is still an open area of research. In this paper, we propose an enhanced unified method for the recognition of handwritten Arabic and Persian numerals using improved structural features. A total of 37 structural based features are extracted and Random Forest classifier is used to classify the numerals based on the extracted features. The results of the proposed approach are compared with other classifiers including Support Vector Machine (SVM), Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN). Four different well-known Arabic and Persian databases are used to validate the proposed method. The obtained average 96.15% accuracy in recognition of handwritten digits shows that the proposed method is more efficient and produces better re...
2019 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE), 2019
The autonomous football robot (ROBO) was designed to enhance the knowledge in the field of roboti... more The autonomous football robot (ROBO) was designed to enhance the knowledge in the field of robotics and computer vision through the robot development. The goal was to learn the use of robotic kits, the Raspberry Pi micro-controller to control the robot motion, the Raspbian operating system (Linux based OS), the python programming language and the computer vision library (OpenCV). The robot design consists of hardware and software designs. For the robot hardware design and implementation, the robotic kit were built, tested, and attached to a 3D custom printing gripper and kicker along with the 180 degrees rotational Raspberry Pi camera by servo motor. Lastly, a small breadboard was attached to set up the pulse, voltage, and the ground for the servo motors. For the robot software design, there are two algorithms or modes in the program, ball mode and goal mode. The ball mode start with ball detection and end with the ball grab. The goal mode start with the goal search and end with kic...
Direct measures provide for the direct examination or observation of student knowledge or skills ... more Direct measures provide for the direct examination or observation of student knowledge or skills against measurable learning outcomes. This paper describes methodology for providing a quantitative measurement of course learning outcomes. The methodology uses a combination of three approaches (average, threshold, and performance vector) to assess course learning outcomes. The method utilizes data obtained from students’ marks in exams, tests, projects, and other formal assessments. A computerized system has been developed based on this method to expedite the analysis process. Keywords--ABET; Assessment tool; Course Learning Outcomes; Key Performance Indicators; Program Learning Outcomes.
A new dataset for Arabic Traffic Signs is developed for the selected most common 24 Arabic traffi... more A new dataset for Arabic Traffic Signs is developed for the selected most common 24 Arabic traffic signs. The dataset consists of 2,718 real captured images and 57,078 augmented images for 24 Arabic traffic signs. The images are captured from three connected cities (Khobar, Dammam and Dhahran) in the Eastern Province of Saudi Arabia. The newly developed dataset consisting of 2,718 real images is randomly partitioned into 80% percent training set (2,200 images) and 20% percent testing set (518) images. Augmented dataset of 57,078 images with 10,878 images for testing and 46,200 images for testing. Due to large file size, the Augmented training dataset is uploaded as two compressed files.
2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), 2021
Conventional streetlight’s constant need for high power and the ill effects it has spawned on the... more Conventional streetlight’s constant need for high power and the ill effects it has spawned on the environmental ecosystem has led researchers to adopt the idea of smart lights in order to minimize energy consumption and maximize power efficiency. This paper proposes S-LIGHT, which is a PWM-based LED adaptive light controlling system that can be deployed at public parks and other outdoor recreational venues, which applies intelligent illumination control of an LED lights. The design is based on Pulse Width Modulation technique which optimizes the overall power consumption and simultaneously supporting a multi-functional and user-friendly post. Smart street lighting aims to make cities feel safer at night, make lights more efficient, and substantially reduce costs of maintenance and energy by integrating sensors and alternative technologies to automate the light. S-LIGHT uses an Arduino UNO board along with a Passive Infrared (PIR) sensor to swiftly increase the brightness of the high-power LED light during the night in the presence of human motion, and a Light Dependent Resistor (LDR) sensor to turn on/off the light by adapting itself to the time of night/day. S-LIGHT also provides a multi-functional post that supports an emergency button feature that easily initiates an Emergency call to the police, a surveillance camera that streams live footage of the area, and an LCD screen that displays to the public awareness messages about the COVID-19 pandemic.
2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), 2018
Deep learning systems have recently gained importance as the architecture of choice in artificial... more Deep learning systems have recently gained importance as the architecture of choice in artificial intelligence (AI). Handwritten numeral recognition is essential for the development of systems that can accurately recognize digits in different languages which is a challenging task due to variant writing styles. This is still an open area of research for developing an optimized Multilanguage writer independent technique for numerals. In this paper, we propose a deep learning architecture for the recognition of handwritten Multilanguage (mixed numerals belongs to multiple languages) numerals (Eastern Arabic, Persian, Devanagari, Urdu, Western Arabic). The overall accuracy of the combined Multilanguage database was 99.26% with a precision of 99.29% on average. The average accuracy of each individual language was found to be 99.322%. Results indicate that the proposed deep learning architecture produces better results compared to methods suggested in the previous literature.
International Journal of Recent Technology and Engineering (IJRTE), 2019
In this study, cloud based innovative methods are introduced that allow users with motor skills i... more In this study, cloud based innovative methods are introduced that allow users with motor skills impairments to access the customized learning platforms. The complete methodology relies on the development of existing technology originally developed for the Gaming Industry; Microsoft Xbox Kinect Sensor. A novel learning platform is developed for teaching students with motor skills impairments and other types of disabilities to learn Quran Recitation. The platform is integrated with a modified Kinect that allows users to access the computer software without the use of a traditional keyboard and mouse. The Kinect then acts as the interface between the uses and software. The system is designed based on the two approaches; hand-free operations via head motion and voice recognition to control the selection of items in the learning platform. For voice recognition, a dataset has also been built for training and initial testing for supervised learning. Extensive tests have been performed that...
2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, 2013
In this paper, we present an application as a solution to problems encountered when using PC'... more In this paper, we present an application as a solution to problems encountered when using PC's by users with motor skills impairment. This application utilizes the Microsoft Kinect Sensor and its Visual Studio SDK to write code that interacts with this novel device originally intended for gaming but now more and more popular with learning, multimedia and entertainment systems. Preliminary results from prototype testing show that the system is usable and has good potential. The intended initial domain of the application is teaching the Muslim holy book (Quran), although the ideas and application software can be adapted as a learning tool for students with disabilities in general.
2019 2nd International Conference on new Trends in Computing Sciences (ICTCS)
Stand along single board computers (SoC) have become so inexpensive and yet so powerful that pave... more Stand along single board computers (SoC) have become so inexpensive and yet so powerful that paved the way for easily developing fully automated systems. SoC systems are equipped with sensors, cameras and various embedded systems that allow developing systems that interact with the surrounding environment. Therefore, the task of capturing images of License plates and using Optical Character Recognition (OCR) techniques to recognize the numerals and characters allows for developing an inexpensive License Plate (LP) Recognition system. LP systems are important and can be used for various application from traffic control, toll payment, and parking access. This paper proposes a Raspberry PI based LP recognition for Arabic/English Characters and Numeral on license plates used in Saudi Arabia. The proposed process utilizes the phases of Preprocessing, Segmentation, Feature Extraction and Classification. At the end of the preprocessing phase, the Characters and Numerals are segmented. Pixel distribution and Horizontal projection profiles are used in the feature extraction phase for the segmented image. Distance Classifier and k-nearest neighbors classifier are used in the classification phase. The proposed system achieved an accuracy of 90.6%. The advantage of such a system is the low cost and portability making it affordable and easily deployable in any location.
2020 IEEE 9th International Conference on Communication Systems and Network Technologies (CSNT)
Computer Vision coupled with Positioning Systems Technology has contributed significantly in assi... more Computer Vision coupled with Positioning Systems Technology has contributed significantly in assisting visually impaired people to independently perform their daily routine tasks. This paper proposes COMPASS, an Indoor Positioning System (IPS) based solution for visually impaired students to move around the university campus independently. COMPASS is a navigation system for the visually impaired students at PMU that consists of three important components which are: an android application running on a smartphone, smart bracelet, and smart shoes. The android application is used to upload student’s class schedule to help them navigate (through Bluetooth based beacons) to and from classes and around the campus. Also, it allows them to call university administrators by simply clicking on a button embedded in the mobile app. The Raspberry Pi based smart bracelet serves as a verification tool (using Tesseract enabled image detection) to ensure that the student arrives at the right class at the right time. As for the smart shoes, it ensures the safety of the student while walking around the campus by detecting obstacles (using ultrasonic sensors) along the way. COMPASS has been extensively tested in a university environment for navigating visually impaired students. COMPASS is economical, small-sized, accurate and uses open source software tools. It can be potentially used for both educational and commercial applications.
2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), 2018
In the digital age, developing an automated system to convert old printed books into digital form... more In the digital age, developing an automated system to convert old printed books into digital form is a challenging task. In this paper we propose a novel technique for the recognition of Arabic scanned documents both with normal and complex layouts. The proposed algorithm is based on the local adaptive thresholding and geometric features which according to the author’s knowledge is the first time it is applied to Arabic document image recognition based on the Physical Layout Analysis (PLA). The proposed method was applied to dataset consisting of 90 images collected from 700 books from various publishers and contains a total of 1112 zones; text zone, image zone, and graphic zone. The proposed algorithm achieved promising results with overall average recognition of 86.71% for Text and Image block regions for all three sets. The proposed novel algorithm outperforms the techniques mentioned in previous literature.
Deferent types of assessment are used to measure the achievements of the Student Learning Outcome... more Deferent types of assessment are used to measure the achievements of the Student Learning Outcomes (SOs) and the Course LearningOutcomes (COs) like direct, indirect, quantitative and qualitative. It is powerful to have a good approach to report the data and automated system for evaluatingthe performance indicators used in the outcomesmeasurement.Since the Student Outcomes are unmeasurable, group of measurable Key Performance Indicators (KPI) are extracted from each SO.In this paper, we propose a new comprehensive combinational approach which utilizes the assessment of the COs and SOs.The combination approach includes Threshold, Average, and Performance Vector used to assess the achievement of the course outcomes. And the KPIs used to measure the achievement of the SO. KeywordsABET; Assessment tool;Student Outcomes; Course Learning Outcomes; Key Performance Indicators.
Data Structure is an important and compulsory course in the computer science and engineering. The... more Data Structure is an important and compulsory course in the computer science and engineering. The topics of the course require detailed view for various algorithms such as queues, stacks, sort, search, trees and graphs. Due to the complexity of teaching and understanding of this course, we are focusing in measuring the student performance and the course learning outcomes. This paper describes methodology for providing a quantitative measurement of data structure course. The methodology uses a combination of three approaches (average, threshold, and performance vector) to assess course learning outcomes. The method utilizes data obtained from students’ marks in exams, tests, projects, and other formal assessments. A computerized system has been developed based on this method to expedite the analysis process.
Journal of Telecommunication, Electronic and Computer Engineering, 2017
With the advances in machine learning techniques, handwritten recognition systems also gained imp... more With the advances in machine learning techniques, handwritten recognition systems also gained importance. Though digit recognition techniques have been established for online handwritten numerals, an optimized technique that is writer independent is still an open area of research. In this paper, we propose an enhanced unified method for the recognition of handwritten Arabic and Persian numerals using improved structural features. A total of 37 structural based features are extracted and Random Forest classifier is used to classify the numerals based on the extracted features. The results of the proposed approach are compared with other classifiers including Support Vector Machine (SVM), Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN). Four different well-known Arabic and Persian databases are used to validate the proposed method. The obtained average 96.15% accuracy in recognition of handwritten digits shows that the proposed method is more efficient and produces better re...
2019 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE), 2019
The autonomous football robot (ROBO) was designed to enhance the knowledge in the field of roboti... more The autonomous football robot (ROBO) was designed to enhance the knowledge in the field of robotics and computer vision through the robot development. The goal was to learn the use of robotic kits, the Raspberry Pi micro-controller to control the robot motion, the Raspbian operating system (Linux based OS), the python programming language and the computer vision library (OpenCV). The robot design consists of hardware and software designs. For the robot hardware design and implementation, the robotic kit were built, tested, and attached to a 3D custom printing gripper and kicker along with the 180 degrees rotational Raspberry Pi camera by servo motor. Lastly, a small breadboard was attached to set up the pulse, voltage, and the ground for the servo motors. For the robot software design, there are two algorithms or modes in the program, ball mode and goal mode. The ball mode start with ball detection and end with the ball grab. The goal mode start with the goal search and end with kic...
Direct measures provide for the direct examination or observation of student knowledge or skills ... more Direct measures provide for the direct examination or observation of student knowledge or skills against measurable learning outcomes. This paper describes methodology for providing a quantitative measurement of course learning outcomes. The methodology uses a combination of three approaches (average, threshold, and performance vector) to assess course learning outcomes. The method utilizes data obtained from students’ marks in exams, tests, projects, and other formal assessments. A computerized system has been developed based on this method to expedite the analysis process. Keywords--ABET; Assessment tool; Course Learning Outcomes; Key Performance Indicators; Program Learning Outcomes.
A new dataset for Arabic Traffic Signs is developed for the selected most common 24 Arabic traffi... more A new dataset for Arabic Traffic Signs is developed for the selected most common 24 Arabic traffic signs. The dataset consists of 2,718 real captured images and 57,078 augmented images for 24 Arabic traffic signs. The images are captured from three connected cities (Khobar, Dammam and Dhahran) in the Eastern Province of Saudi Arabia. The newly developed dataset consisting of 2,718 real images is randomly partitioned into 80% percent training set (2,200 images) and 20% percent testing set (518) images. Augmented dataset of 57,078 images with 10,878 images for testing and 46,200 images for testing. Due to large file size, the Augmented training dataset is uploaded as two compressed files.
2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), 2021
Conventional streetlight’s constant need for high power and the ill effects it has spawned on the... more Conventional streetlight’s constant need for high power and the ill effects it has spawned on the environmental ecosystem has led researchers to adopt the idea of smart lights in order to minimize energy consumption and maximize power efficiency. This paper proposes S-LIGHT, which is a PWM-based LED adaptive light controlling system that can be deployed at public parks and other outdoor recreational venues, which applies intelligent illumination control of an LED lights. The design is based on Pulse Width Modulation technique which optimizes the overall power consumption and simultaneously supporting a multi-functional and user-friendly post. Smart street lighting aims to make cities feel safer at night, make lights more efficient, and substantially reduce costs of maintenance and energy by integrating sensors and alternative technologies to automate the light. S-LIGHT uses an Arduino UNO board along with a Passive Infrared (PIR) sensor to swiftly increase the brightness of the high-power LED light during the night in the presence of human motion, and a Light Dependent Resistor (LDR) sensor to turn on/off the light by adapting itself to the time of night/day. S-LIGHT also provides a multi-functional post that supports an emergency button feature that easily initiates an Emergency call to the police, a surveillance camera that streams live footage of the area, and an LCD screen that displays to the public awareness messages about the COVID-19 pandemic.
2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), 2018
Deep learning systems have recently gained importance as the architecture of choice in artificial... more Deep learning systems have recently gained importance as the architecture of choice in artificial intelligence (AI). Handwritten numeral recognition is essential for the development of systems that can accurately recognize digits in different languages which is a challenging task due to variant writing styles. This is still an open area of research for developing an optimized Multilanguage writer independent technique for numerals. In this paper, we propose a deep learning architecture for the recognition of handwritten Multilanguage (mixed numerals belongs to multiple languages) numerals (Eastern Arabic, Persian, Devanagari, Urdu, Western Arabic). The overall accuracy of the combined Multilanguage database was 99.26% with a precision of 99.29% on average. The average accuracy of each individual language was found to be 99.322%. Results indicate that the proposed deep learning architecture produces better results compared to methods suggested in the previous literature.
International Journal of Recent Technology and Engineering (IJRTE), 2019
In this study, cloud based innovative methods are introduced that allow users with motor skills i... more In this study, cloud based innovative methods are introduced that allow users with motor skills impairments to access the customized learning platforms. The complete methodology relies on the development of existing technology originally developed for the Gaming Industry; Microsoft Xbox Kinect Sensor. A novel learning platform is developed for teaching students with motor skills impairments and other types of disabilities to learn Quran Recitation. The platform is integrated with a modified Kinect that allows users to access the computer software without the use of a traditional keyboard and mouse. The Kinect then acts as the interface between the uses and software. The system is designed based on the two approaches; hand-free operations via head motion and voice recognition to control the selection of items in the learning platform. For voice recognition, a dataset has also been built for training and initial testing for supervised learning. Extensive tests have been performed that...
2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, 2013
In this paper, we present an application as a solution to problems encountered when using PC'... more In this paper, we present an application as a solution to problems encountered when using PC's by users with motor skills impairment. This application utilizes the Microsoft Kinect Sensor and its Visual Studio SDK to write code that interacts with this novel device originally intended for gaming but now more and more popular with learning, multimedia and entertainment systems. Preliminary results from prototype testing show that the system is usable and has good potential. The intended initial domain of the application is teaching the Muslim holy book (Quran), although the ideas and application software can be adapted as a learning tool for students with disabilities in general.
Uploads
Papers by Loay Alzubaidi