The aim of image colorization is to add colors to a gray image such that the colorized image is perceptually meaningful and visually appealing. In this way, old images that have been reached from past to present can be visualized in different ways and presented to people.
In this project, video colorization done by using the model that uses Convolutional Neural Networks to colorize images. In this study, which reference-based colorization is used, the frames in the video are colorized according to a reference photo which is determined by system. The scene transitions occurring within the video have been identified and a system has been designed which automatically suggests a suitable reference photo for the content of each scene.