Browsing by Author "Tarek Ibrahim, Omar"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Forensic Document Examination For Handwritten Signatures Using Deep Learning
    (October University For Modern Sciences and Arts, 2022) Tarek Ibrahim, Omar
    Forgery is a type of fraud de ned as the act of forging a copy or an imitation of a document, signature, or banknote which is considered a form of illegal criminal activity. In this project, we are focusing on developing an application that aims to help forensic examiners in the process of identi cation and detection of handwritten signature forgeries inside documents in addition to the identi cation of possible types of signature forgery methods. The proposed system uses contemporary methods that utilize a deep learning approach of CNNs (Convolutional Neural Networks) based on both binary, and categorical image classi cation methodologies to help forensic examiners measure the genuineness of handwritten signatures. For the image classi cations, we have considered using a number of ve di erent CNN models which are: VGG-16, ResNet50, Inception-v3, Xception, and our 2DCNN model. The purpose of using these di erent CNN models is to conduct a comparative study between each of the models to help determine which model is more e cient at identifying images containing text data of similar resemblances, as to the nature of handwritten signatures. Upon comparing these CNN models, we concluded that the ResNet50 model was able to reach the highest score at identifying handwritten signatures with an accuracy of 82.3% and 86% when tested on datasets of 300 images and 140 images respectively. The system aims to provide all functionalities which are required by current standards through the use of robust system architecture, design patterns, and various techniques to build a practical application that follows an expandable structure.
  • Thumbnail Image
    Item
    Kid-ML: ML For Kidney Malignant Tissues Identification
    (October university for modern sciences and Arts MSA, 2023) Gamal Ramadan, Al-Shaimaa; Tarek Ibrahim, Omar; M. D. E. Hassanein, Ahmed
    stract A considerable worldwide medical and health burden is imposed by kidney disease due to its high rates of morbidity and death as well as its high economic cost. Imaging tests can be used by doctors to detect kidney tumors or other diseases. Imaging studies include Magnetic Resonance Imaging(MRI), Computed Tomography(CT) scan, and ultrasound scan which consume a lot of time from doctors to detect kidney cancers through them. In order to help doctors to identify tumors in their early stages, they can use simple Machine Learning(ML) techniques or Deep Learning techniques through diagnostics and predictions applications. A rise in interest in deep learning algorithms, which are Artificially Intelligently (AI) based, on a worldwide scale has enabled recent improvements in medical imaging and kidney segmentation. Deep Learning techniques which are AI-based can offer and identify the kidney tumor in a more efficient method, allowing for the development of a more effective kidney tumor detection system. An input layer, one or more hidden layers, and an output layeare the components of Artificial Neural Networks(ANNs) which is one kind of Deep Learning(DL) algorithm that imitates biological neurons. Another kind is Convolutional Neural Networks(CNNs) which are often the most effective and well-liked in computer vision for image categorization in medical imaging. Deep learning techniques based on CNNs have shown promising results in a variety of medical image processing applications. However; all deep learning techniques consume very high computational power. In this work, we study the use of simple machine learning algorithms such as Decision Tree(DT), K Nearest Neighbor(KNN), Random Forest(RF) and Logistic Regression(LR) algorithms and compare their results. Simple machine learning algorithms consumes minimum computational power. We discuss the behavior of those machine learning algorithms while changing the resolution of the images. We found that the accuracy of simple machine learning algorithm is stable while decreasing the resolution of images to be 32pixels.