Implementation of Deep Learning Model for Video Colorization

Abstract

Technology sometimes enhances the art and also Vandalizes. Colorizing black and white films is a very old idea dating back to 1902. For decades many movie creators opposed the idea of colorizing their black and white movies and thought of it as vandalism of their art. Today it is accepted as an enhancement to the art form. The technology itself has moved from painstaking hand colorization to today's largely automated techniques. In the last few years, with the Deep Learning revolution, automation in colorization has taken a huge leap forward. In this project, one such Deep Learning model for video colorization will be proposed and present a simple colorization methodin which the model performs object detection and imparts color based on the trained dataset to the input feed. A machine learning model have been built to automatically turn grayscale video feed into a colored video feed based on a specific dataset.