We are going to develop an automatic image colorization project. Here we work on the deep neural network. In this project we train our model and by training we predict the pixels color. This intermediate output help to colorize the grayscale image to color image. There are various methods to colorize the image but, in this project, we are using Tensor Flow to change the grayscale image into color image. This uses self-supervised learning feature and train thousands of the images and finally predict the color of the image. The predicted color is totally depending on the training of images. We leverage an existing large-scale scene database to train our model to learn the global priors and classify the objects of image to be able to map color to it. We demonstrate our method extensively on many different types of images, including black-and-white photography from over a hundred years ago, and show realistic colorizations.
How to Cite
International Journal of Engineering Technology and Computer Research (IJETCR) by Articles is licensed under a Creative Commons Attribution 4.0 International License.