This application is related to image processing based on CNN (Convolution Neural Network). The basic idea behind this project is to convert black and white images to colored image. We are using Convolution Neural Network capable of coloring black and white images.
Image colorization is the process of taking an input grayscale (black and white) image and then producing an output colorized image that represents the semantic colors tones of the input.
We have started with the ImageNet dataset and converted all images from the RGB color spaces to the lab color space. Similar to the RGB color spaces, the lab color space has three channels. But unlike the RGB color space, lab encodes color information differently:
- the L channel encodes lightness intensity
- The A channel encodes green-red
- And the B channel encodes blue-yellow
The main concept behind this colorization is :
- Convert all training images from the RGB color space to the lab color space
- Use the L channel as the input to the network and train the network to predict the AB channel
- Combine the input L channel with the predicated AB channels
- Convert the LAB image back to RGB
This page is contributed by Lee Zaa . If you like AIHUB and would like to contribute, you can also write an article & mail your article to email@example.com . See your articles appearing on AI HUB platform and help other AI Enthusiasts.