In this video, we will learn how to colorize black and white images using OpenCV, Deep Learning, and Python.
Image colorization is the process of taking an input grayscale (black and white) image and then producing an output colorized image.
The approach we are going to use here relies on deep learning. We will utilize a Convolutional Neural Network capable of colorizing black and white images with results that can even “fool” humans!
Download the model files:
1. colorization_deploy_v2.prototxt: https://github.com/richzhang/colorization/tree/caffe/colorization/models
2. pts_in_hull.npy: https://github.com/richzhang/colorization/blob/caffe/colorization/resources/pts_in_hull.npy
3. colorization_release_v2.caffemodel: https://www.dropbox.com/s/dx0qvhhp5hbcx7z/colorization_release_v2.caffemodel?dl=1
Credits:
1. https://github.com/opencv/opencv/blob/master/samples/dnn/colorization.py
2. http://richzhang.github.io/colorization/
3. https://github.com/richzhang/colorization/
GitHub: https://github.com/balajisrinivas/Colorizing-black-and-white-images-using-Python/tree/master
LinkedIn: https://www.linkedin.com/in/balaji2512/
0:00 Introduction and Demo
1:35 Idea behind colorizing black and white images
3:52 Install Dependencies
4:26 Credits to OpenCV and Zhang et al.
4:58 Import statements
5:23 Download the model files
6:09 Let's code it
11:59 Run the program
12:55 End Notes
