Film Colorization Using Texture Feature Coding and Artificial Neural Networks

In this paper a novel method for machine-based black and white films colorization is presented. The kernel of the proposed scheme is a trained artificial neural network which maps the frame pixels from a grayscale space into a color space. We employ the texture coding method to capture the line/texture characteristics of each pixel as its most significant gray scale space feature, and using that feature, expect a highly accurate B/W to color mapping from the ANN. The ANN would be trained by the B/W-color pairs of an original reference frame. The experiments performed on some typical video footages show the advantages of the proposed method in both visual and mathematical aspects. Different color spaces are also tried to obtain the optimum colorization performance.