Saab Khalid Al bdrani

Year: 2025

Academic Degree: Master

Supervisor Type: Supervisor

Supervisor State: In Progress

Develop A System for Anemia Detection by Application of Deep Learning Models

Huda Salim Jasim

Year: 2024

Academic Degree: Master

Supervisor Type: Supervisor

Supervisor State: Graduated

Design and Implementation of Smart Reader Glasses for the Blind and Visually Impaired

Maad Anwar Ismael AL-Hadithy

Year: 2024

Academic Degree: Diploma

Supervisor Type: Supervisor

Supervisor State: Graduated

Computer Vision-Based Smoke and Fire Detection

Nama'a Manhal Zakoor

Year: 2024

Academic Degree: Master

Supervisor Type: Supervisor

Supervisor State: Graduated

Design and Implementation a Robust System for Detecting Counterfeit Iraqi Currencies Based on Deep Learning Techniques

Younis Bashar Younis Kashmola

Year: 2024

Academic Degree: Master

Supervisor Type: Supervisor

Supervisor State: Graduated

Retinal Detachment Detection System Based on Deep Learning Algorithms

Ruaa Mutasem Saadallah

Year: 2022

Academic Degree: Master

Supervisor Type: Supervisor

Supervisor State: Graduated

A Real-Time of Face Mask Recognition System for Human Safety

Gona Mohammed Dhahir

Year: 2022

Academic Degree: Master

Supervisor Type: Supervisor

Supervisor State: Graduated

Real-Time Human Detection and Tracking Based on Deep Learning Technique for Social Distance

Zainab Mohammed Hussien

Year: 2019

Academic Degree: Master

Supervisor Type: Co-supervisor

Supervisor State: Graduated

Image Processing of Two Camera System for Vision Used in Automated System Using Deep Learning

Ph.D

Jan 13, 2014 - Dec 30, 2018

Remote Sensing- Image Processing

Masters

Sep 5, 1999 - Feb 13, 2002

Remote Sensing- Image Processing

Bachelors

Sep 1, 1986 - Jul 1, 1990

Electrical Engineering

Faculty [Faculty member]

Jun 14, 2002 - Present

graduate students' projects [Supervising of graduate students' projects]

Jan 4, 2019 - Present

exam commission [Member of the exam commission]

Jan 3, 2010 - Present

undergraduate students' projects [Supervising of undergraduate students' projects]

Jan 1, 2019 - Present

A Technique for Retinal Detachment Detection Manipulating YOLOv8 Models

Mar 22, 2025

Journal NTU Journal of Engineering and Technology

DOI 10.56286/rxck4y17

Issue No. 1

Volume Vol. 4

A retinal detachment is a serious condition resulting in the retina detaching from its support layers, which are just beneath it. If untreated, this can cause blindness. To detect the classes of retinal detachment in various images, this paper introduces a novel method employing deep learning techniques involving the YOLOv8 algorithm. Notably, this marks the first use of the YOLOv8 model for retinal detachment detection. Retinal detachment can be identified with high precision using images obtained from Optical Coherence Tomography (OCT). The proposed work assesses the performance of these models using metrics such as mAP50, recall, andprecision by training five YOLOv8 models: YOLOv8n, YOLOv8s,YOLOv8m, YOLOv8l, and YOLOv8x. Among these, the YOLOv8smodel had the best performance with a mAP50 of 0.985, a recall of 0.97,and a precision of 0.968. The other models had the following mAP scores:YOLOv8n (0.949), YOLOv8m (0.906), YOLOv8l (0.889), and YOLOv8x(0.907). This demonstrates that the proposed system works effectively in detecting retinal detachment, resulting in highly accurate results mined from complex medical data sets and imaging, thereby making it an important tool in medicine (PDF) A Technique for Retinal Detachment Detection Manipulating YOLOv8 Models. Available from: https://www.researchgate.net/publication/390130970_A_Technique_for_Retinal_Detachment_Detection_Manipulating_YOLOv8_Models [accessed Apr 05 2025].

Read Publication

Advanced Methods for Identifying Counterfeit Currency: Using Deep Learning and Machine Learning

Sep 26, 2024

Journal NTU Journal of Engineering and Technology

DOI 10.56286/ntujet.v3i3.944

Issue No. 3

Volume Vol. 3

Counterfeiting is a serious threat to economies because sophisticatedcounterfeit banknotes are becoming increasingly difficult to identifythrough conventional verification techniques, thanks to advancements inprinting technology. In this work, we offer a thorough investigation ofsophisticated methods for detecting counterfeit money that make use ofdeep learning and machine learning approaches. Using machine learningalgorithms like Random Forest, Decision Tree Classifier, XGBoost,CatBoost, and Support Vector Machine (SVM) in addition to deeplearning techniques like Convolutional Neural Networks (CNNs),VGG16, MobileNetV2, and InceptionV3, we examine the securitycharacteristics of Iraqi dinar banknotes and build robust models. All of themodels in our results had high accuracy rates, with CNN, CatBoost, andSVM showing particularly strong performance. These results demonstratehow effective cutting-edge technical solutions are in thwarting the dangersposed by counterfeit money, protecting national economies and reducinglosses. Sustaining the security of international financial systems and keeping ahead of evolving counterfeiting strategies need ongoing studyand development in this area

Read Publication

Develop a Robust System for Detecting Counterfeit IraqCurrencies Based on Deep Learning Techniques

May 27, 2024

Journal Journal of Computational Analysis and Applications

DOI 10.56286/ntujet.v3i3.944

Issue No. 2

Volume VOL. 33

Counterfeiting poses a serious threat to the financial economy because advanced counterfeit banknotes,thanks to advances in printing technology, have become difficult to identify through traditionalinvestigation techniques. Maintaining the security of international economic systems and keeping pacewith evolving counterfeiting strategies requires continuous study and development in this field. TheCentral Bank of Iraq is the exclusive management responsible for issuing local currency, so verifying theauthenticity of Iraqi currency is of utmost importance to maintain the integrity of the country's financialeconomy. This thesis aims to develop a reliable system for detecting counterfeit Iraqi currency that candistinguish the subtle differences between real and counterfeit Iraqi currency. This work utilizes machinelearning algorithms such as Random Forest, XGBoost, Decision Tree Classifier, Support Vector Machine(SVM), and CatBoost. In addition, deep learning models such as Convolutional Neural Networks (VGG16,InceptionV3, MobileNetV2) were employed to allow counterfeit banknote detection with high accuracyand reliability.The proposed system was trained on a dataset of 1359 images that include two types ofIraqi currencies (real and counterfeit with the highest level of professionalism) and in different categories,as they were collected in cooperation with the Central Bank of Iraq after obtaining official approvals fromthe relevant authority. The dataset underwent initial processing using augmentation and annotationtechniques to increase the dataset number to improve the network's performance in the training processconcerning prevalent feature extraction and thus achieve high detection accuracy, becoming 4188 for realcurrencies and 3966 for counterfeit currencies. The dataset was divided into 80% for training and 20%for validation. In this work, a real-time system was built and implemented based on a set of maincomponents including Raspberry Pi5, Raspberry Pi camera, servo motor, and LCD screen. The devicediscovers the Iraqi currency using a camera and a servo motor supported by UV light to capture thecurrency image to ensure the highest clarity and accuracy. The image is sent to pre-trained deep learningand machine learning models to classify it as counterfeit or real. Finally, the detection result is displayedon an LCD screen. The experimental results in which CatBoost and SVM were used showed an accuracy ofup to 98%, while the accuracy of the CNN model ranged to 99%. These results demonstrated theeffectiveness of advanced technical solutions in thwarting the risks posed by counterfeit money,protecting the financial economy, and reducing losses

Read Publication

A COMPREHENSIVE EVALUATION OF YOLOv5s AND YOLOv5m FOR DOCUMENT LAYOUT ANALYSIS

Jan 19, 2024

Journal European Journal of Interdisciplinary Research and Development

Issue (2024)

Volume Volume-23

Document Layout Analysis (DLA) in images, is highly dynamic within computer vision. Presently, deep learning architectures, particularly YOLOv5s and YOLOv5m, take the forefront in addressing this challenge This paper meticulously examines their performance, both qualitatively and quantitatively, measured by Average Precision (AP) on COCO datasets. Significant improvements are observed through fine-tuning specific datasets, notably books in Arabic and English languages. A comparative evaluation of YOLOv5m and YOLOv5s in the realm of DLA unfolds. Despite YOLOv5s showcasing an impressive Frames Per Second (FPS) of 123, surpassing YOLOv5m by 2 units, the latter proves to be the optimal model for DLA systems. Its comprehensive performance superiority shines through, boasting an mAP of 94.2%, outperforming other models in this study. Noteworthy is YOLOv5m's lower FPS, compensated by its respectable detection speed, rendering it a pragmatic choice for real-world applications where accuracy is paramount

Read Publication

NTEGRATIVE DETECTION OF RETINAL DETACHMENT WITH ALEXNET AND HEAT MAPS VISUALIZATION

Jan 13, 2024

Journal Mathematics for Applications

DOI 0.13164/ma.2024.13108

Issue 1805-3629

Volume Vol. 13. No. 1.

This study at investigates the application of the Alex Net convolutional neural network with heatmap visualizations for detecting retinal detachment (RD).Using a dataset of optical coherence tomography (OCT) pix classified into four categories—choroidal neovascularization (CNV), diabetic macular edema (DME), DRUSEN, and NORMAL—the version done good consequences. Alex Net's deep mastering skills yielded a one hundred% accuracy rate in classifying those conditions. Grad-CAM heatmap visualizations furnished insights into the model's decision-making process through highlighting important picture regions influencing each prediction. This approach no longer best more suitable diagnostic accuracy however additionally progressed interpretability, making the model's outputs extra transparent and clinically

Read Publication

Masked Face Detection And Identification By Using Deep Learning Technology

Aug 20, 2022

Journal Neuroquantology

DOI 10.14704/nq.2022.20.8.NQ44778

Issue No 8

Volume Volume 20

In the wake of the global health disaster brought on by the globally circulating COVID-19 coronavirus. It is currently a research topic in many fields, especially those interesting such as artificial intelligence and new information technologies. Many regulatory agencies now require wearing face masks, particularly in crowded areas involving regular and large-scale human interaction, like inside overcrowded transit facilities, where everyone must wear masks. It is challenging to identify the identity of a person using conventional facial recognition techniques, so it needs developed technology with high accuracy. The paper presents a new system by utilizing the advanced MobileNetV2 network to recognize the person's identity without the need to take off the face mask. The proposed system has trained by using different eight classes of regular people's faces (without wearing face masks) under diverse environmental conditions. The performance of the proposed system demonstrated high efficiency in identifying the identity of the person accurately up to 100%. The recognition process was achieved using Keras with TensorFlow in terms of accuracy and detection speed.

Read Publication

Real-Time Human Detection and Tracking Based on Deep Learning Technique

May 20, 2022

Journal Neuroquantology

DOI 10.14704/nq.2022.20.6.NQ22202

Issue No 6

Volume Volume 20

In the field of computer vision, the detection of an object such as a human is critical for image understanding. Human tracking detection in real-time helps in providing critical information for a vast variety of intelligent system applications. This paper presents a new model for real-time human tracking detection (RTHTD) for surveillance video by using a deep learning technique based on the modified YOLOv5 model, the backbone of the modified model formed from Cross Stage Partial(CSP ), Bottleneck, and SPPF

Read Publication

Social Distancing Monitoring by Human Detection Through Bird’s-Eye View Technique

Feb 27, 2024 - Feb 29, 2024

Publisher VISAPP 2024 - 19th International Conference on Computer Vision Theory and Applications

DOI 10.5220/0012373900003660

Country Italy

Location Rome

Visit Conference

Building A Face Mask Recognition System Supported withFacial Landmark Features in Real-Time

Jun 29, 2022 - Jun 30, 2022

Publisher AIP Publishing. 978-0-7354-4741-7

DOI 10.1063/5.0172307

Country Iraq

Location Nineveh

Visit Conference