Mahmoud GHonem's repositories
Social-Media-Image-Analyzer
Detect information from social media images using image processing, computer vision, Amazon Rekognition, and deploying the system using Flask on AWS. We extract information from the images like "the number of likes", "date the image was posted", "privacy", and "number of viewers" for a given image on social media platforms.
Bills-Extractor
Extract bills with specific patterns from texts using regx
draw__yolo_box_coordinates_on_image
In this repo, I wrote python script that take the output bounding box of Yolo and the text, and then draw them on the image
Egyptian-Currency-Detection-using-YoloV5
Using artificially Generated currency Dataset with YoloV5 to build currency detection model
FineTuining-Yolov5-model-using-old-model-and-videos
We Have old yolo v5 with few videos for the objects in the new environment, Here we will semi-automate re-training this model
Get_dominant_color_in_image
How to get the most dominant color/ colors in an image
Hands-on-ML-Notebooks-and-Solutions-
In the Repo, I'll write all the codes and important details from "Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow"
Image-Data-Generation
Image Data Generation code will help you when you suffer from the leakage of data, with few images you will be able to build a dataset with hundred of thousands of images
Implementation-of-menu-project-using-oo
This is an implementation of CH2 Case study from "Python 3 Object-Oriented Programming" book
pedestrian-detection
In this repo, I've used OpenCV to detect pedestrians. You will find two functions:
Python-Data-Structres
Some notes, summary, and codes for "Mastering critical SKILLS in Data Structures using Python" Course
Scraping-Coursera-using-Selenium
In this ipynb file, I've Used-Selenium-for scraping categories of Coursera, and data about courses at each category.