Pinned Repositories
ASL-Recognition-with-DeepLearning
American Sign Language (ASL) is the primary language used by many deaf individuals in North America, and it is also used by hard-of-hearing and hearing individuals. The language is as rich as spoken languages and employs signs made with the hand, along with facial gestures and bodily postures.
AWS-Computer-Vision-GluonCV
AWS Computer Vision: Getting Started w ith GluonCV
Build-Basic-Generative-Adversarial-Networks-GANs-
Started my journey with GANs: 1- Generative adversarial network (GAN) 2- Deep Convolutional GAN (DCGAN) 3- Wasserstein GAN with Gradient Penalty (WGAN-GP) 4- Conditional GAN 5- Controllable Generation
Camera-Calibration
Find unknown Intrinsic and Extrinsic camera parameter (o = K [R|t] O), Intrinsic Matrix are Parameters component internal to the camera such as (focal length, geometry and radial distortion coefficients of the lens) and use to project Point from camera coordinate to image plan. Extrinsic Matrix are Parameters of camera position [R|t].External to camera and specific to location camera in world coordinate frame. Used to transform 3D point from world to camera coordinate.
COVID-19_Segmentation
Automatic Segmentation using Artificial intelligence to: Left Lung Right Lung COVID-19 in CT images and Determine the location of diseases and the rate of occurrence in the lung.
Digital-Signal-Processing-Package
This system aim to cover most of part in Signal Processing using Simple GUI to allow to any user to practice and understand the signals and this system divided to several part : 1. 2. 3. 4. 5. 6. 7. 8. Main Window. Signals. Quantization and Encoding. Discrete Fourier Transform (DFT) and (Inverse DFT). Fast Fourier Transform (FFT). Operation On Signals. Convolution and Correlation. Filters and Sampling.
Features-Detection-Describtion-and-Matching
A Comparative Analysis of SIFT, SURF, AKAZE, ORB, BRIEF and BRISK
Histogram-of-Oriented-Gradients-HOG-
HOG descriptors: are mainly used to describe the structural shape and appearance of an object in an image, making them excellent descriptors for object classification. However, since HOG captures local intensity gradients and edge directions, it also makes for a good texture descriptor.
Non-Local-means-filter
Non-local mean filter is an algorithm in image processing for image denoising. Like other algorithm, it based on the basic remark: denoising is achieved by averaging.
Person-re-identification-using-Siamese-Network
Train the network with the Triplet loss function and create Anchor, Positive and Negative image dataset, which will be the inputs of triplet loss function, through which the network will learn feature embedding.
Mahmoud-Ali-FCIS's Repositories
Mahmoud-Ali-FCIS/Digital-Signal-Processing-Package
This system aim to cover most of part in Signal Processing using Simple GUI to allow to any user to practice and understand the signals and this system divided to several part : 1. 2. 3. 4. 5. 6. 7. 8. Main Window. Signals. Quantization and Encoding. Discrete Fourier Transform (DFT) and (Inverse DFT). Fast Fourier Transform (FFT). Operation On Signals. Convolution and Correlation. Filters and Sampling.
Mahmoud-Ali-FCIS/Features-Detection-Describtion-and-Matching
A Comparative Analysis of SIFT, SURF, AKAZE, ORB, BRIEF and BRISK
Mahmoud-Ali-FCIS/Non-Local-means-filter
Non-local mean filter is an algorithm in image processing for image denoising. Like other algorithm, it based on the basic remark: denoising is achieved by averaging.
Mahmoud-Ali-FCIS/Person-re-identification-using-Siamese-Network
Train the network with the Triplet loss function and create Anchor, Positive and Negative image dataset, which will be the inputs of triplet loss function, through which the network will learn feature embedding.
Mahmoud-Ali-FCIS/Build-Basic-Generative-Adversarial-Networks-GANs-
Started my journey with GANs: 1- Generative adversarial network (GAN) 2- Deep Convolutional GAN (DCGAN) 3- Wasserstein GAN with Gradient Penalty (WGAN-GP) 4- Conditional GAN 5- Controllable Generation
Mahmoud-Ali-FCIS/Camera-Calibration
Find unknown Intrinsic and Extrinsic camera parameter (o = K [R|t] O), Intrinsic Matrix are Parameters component internal to the camera such as (focal length, geometry and radial distortion coefficients of the lens) and use to project Point from camera coordinate to image plan. Extrinsic Matrix are Parameters of camera position [R|t].External to camera and specific to location camera in world coordinate frame. Used to transform 3D point from world to camera coordinate.
Mahmoud-Ali-FCIS/ASL-Recognition-with-DeepLearning
American Sign Language (ASL) is the primary language used by many deaf individuals in North America, and it is also used by hard-of-hearing and hearing individuals. The language is as rich as spoken languages and employs signs made with the hand, along with facial gestures and bodily postures.
Mahmoud-Ali-FCIS/AWS-Computer-Vision-GluonCV
AWS Computer Vision: Getting Started w ith GluonCV
Mahmoud-Ali-FCIS/COVID-19_Segmentation
Automatic Segmentation using Artificial intelligence to: Left Lung Right Lung COVID-19 in CT images and Determine the location of diseases and the rate of occurrence in the lung.
Mahmoud-Ali-FCIS/Direct-Linear-Transform
Direct linear transformation (DLT) is a method of determining the three dimensional location of an object (or points on an object) in space using two views of the object.
Mahmoud-Ali-FCIS/Fitting-an-Ellipse-
Suppose P a convex Ellipse with unknown parameters and P1, . . . , Pn. are some random points, so we want to Find an ellipse E that is as close as possible to P1, . . . , Pn.
Mahmoud-Ali-FCIS/HCI-Project
Mahmoud-Ali-FCIS/ImageSegmentation-of-Handwritten-Digits
Image Segmentation of Handwritten Digits: build a Convolutional Neural Network (CNN) from scratch for the downsampling path and use a Fully Convolutional Network, FCN-8, to upsample and produce the pixel-wise label map. The model will be evaluated using the intersection over union (IOU) and Dice Score.
Mahmoud-Ali-FCIS/Julia_DL
Deep Learning (Julia)
Mahmoud-Ali-FCIS/Julia_Fundamental
Fundamental of Julia
Mahmoud-Ali-FCIS/Julia_ML
Machine Learning (Julia)
Mahmoud-Ali-FCIS/Machine-Learning-Package
Machine Learning Package
Mahmoud-Ali-FCIS/Morphological-Transformations
Morphological transformations are some simple operations based on the image shape. It is normally performed on binary images. It needs two inputs, one is our original image, second one is called structuring element or kernel which decides the nature of operation. Two basic morphological operators are Erosion and Dilation. Then its variant forms like Opening, Closing, Gradient
Mahmoud-Ali-FCIS/Naive-Bees-DeepLearning-with-Images
Can a machine distinguish between a honey bee and a bumble bee? Being able to identify bee species from images, while challenging, would allow researchers to more quickly and effectively collect field data. In this project, you will build a simple deep learning model that can automatically detect honey bees and bumble bees, then load a pre-trained model for evaluation. You will use keras, scikit-learn, scikit-image, and numpy, among other popular Python libraries.
Mahmoud-Ali-FCIS/Naive-Bees-Predict-Species-from-Images
Can a machine distinguish between a honey bee and a bumble bee? Being able to identify bee species from images, while challenging, would allow researchers to more quickly and effectively collect field data. In this project, will use the Python image library Pillow to load and manipulate image data, then build a model to identify honey bees and bumble bees given an image of these insects
Mahmoud-Ali-FCIS/NeuralTeks
Cloud solution that identifies the type and number of organisms on a culture medium using a simple photo.
Mahmoud-Ali-FCIS/ObjectPoseEstimationSummary
Resources (papers, datasets, rendering methods) in the domain of object pose estimation.
Mahmoud-Ali-FCIS/Play_with_Pytorch
1- Building an image classifier using (CNN) 2- Discover Recurrent neural networks (RNN) by building a character-level RNN classifying different names into different languages.
Mahmoud-Ali-FCIS/Portfolio-Mahmoud-Ali
Mahmoud-Ali-FCIS/Recycling_errors
WELCOME TO RECYCLING ERRORS Computer vision system for automatic monitoring of trash for garbage collection trucks.The goal of the vision system is to assess the ratio of recyclable and non-recyclable garbage.
Mahmoud-Ali-FCIS/Recycling_errors_app
Recycling errors streamlit app deployed on heroku
Mahmoud-Ali-FCIS/Self-organizing-map-Kohonen
A self-organizing map (SOM) is a type of artificial neural network (ANN) that is trained using unsupervised learning to produce a low-dimensional (typically two-dimensional), discretized representation of the input space of the training samples, called a map, and is therefore a method to do dimensionality reduction
Mahmoud-Ali-FCIS/Unsupervised_Anomaly_Detection_Brain_MRI
Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study
Mahmoud-Ali-FCIS/wowchemy-hugo-themes
🔥 Hugo website builder, Hugo themes & Hugo CMS. No code, build with widgets! 创建在线课程，学术简历或初创网站。
Mahmoud-Ali-FCIS/Zombies_Detection
Object Detection API and retrain RetinaNet to spot Zombies using just 5 training images