b7b_el_cima

Content

• Overview

• Specifications

• Model Architecture

• How to use?

• Examples

• Our Team

• License

---

Overview

Academic project of an application that converts black and white videos or images into colored and nice ones. For more, check our Project Proposal and Video

---

Specifications

A simple website containing a colorization app for video or image

• The front-end is in HTML5, CSS3, Javascript, Ajax and Bootstrap 4.

• The back-end is in Python 3 using Flask framework.

• Model Architectures are written using Keras.

• The Core project is developed using Tensorflow and OpenCV.

• Models Training is done using Colab

• Development is OS independent.

---

Model Architecture

• We learned 3 different architectures you can find all details here.

• By comparing the initial results of them the one which gave the best result was U-Net so we continue training on it.

• We trained it by 66k images from old colored movies. you can find the dataset here.

• The training took 2 days on colab to make 20 epochs with batch size 32.

---

How to use?

1) Download this repo

• From GitHub: Clone or Download the repository or
• From Git:

  git clone https://github.com/SuperMoudy/b7b_el_cima

2) Download the model

• Create a new folder in the repo and name it "models"
• In this folder(models), download the model from here

3) Install dependencies

• Using command line:

  pip install -r requirements.txt

4) To run the website

• Go to the project directory
• Go to Web App
• Run command line there and type:

  python abbas.py

5) To colorize an Image:

• Include a url or upload an image then click Colorize:

  

6) To colorize a Video:

• Upload a video then click Colorize:

  

---

Examples

Image

Video

Our Team

• Aladdin Mostafa
• Mohamed Hussein
• Rawan Mahmoud
• Mado Mohamed
• SuperMoudy

---

License