afnan algogandi's Projects
AfnanCV is an image processing tool that allows users to edit and modify images using various tools.
It is an Arabic Dialect Identification system. Its task is to identify the Arabic language dialect in a text format. It is challenging due to the high variability of Arabic dialects and the lack of large-scale annotated datasets.
This project implements an attendance system using facial recognition. A deep learning model is built from scratch to identify faces in a video stream from a webcam. The model is trained on a dataset of images of people to be recognized and validated on a separate dataset. The attendance of recognized people is recorded in an Excel worksheet.
All the codes of the artificial intelligence camp (applications in computer vision and image processing) Google Club for developer students
Eye Disease Classification using google images data
face recognition using openCV library in python
This project implements a Fashion Product Recommendation System (FRS) using a pre-trained ResNet50 model for feature extraction and the Annoy algorithm for finding similar products. The system allows users to input an image of a fashion product and receives recommendations for similar products.
Processing and multiplying images to increase the accuracy of the model when training
Building the K-means and DBSCAN algorithm from the scratch, which is considered one of the machine learning algorithms
coloring game by JAVA, GUI
find the best meal with the lowest cost and lowest calories (Minimize the calories and the cost)
coloring game by JAVA, HTML
The smart home farmer takes care of the plants, uses Arduino, soil moisture sensor to control the watering process while also providing light to the plant. Robot Gardener will protect the soil ecosystem while delivering water at optimal levels for the plantโs growth.
Self Service Supermarket by Prolog language
developed a model that can predict air temperature according to atmospheric pressure.
This code takes an Arabic text description as input, translates it to English using Google Translate, and generates a video sequence that matches the translated text description. It utilizes a pre-trained model and diffusion techniques to create the video content.