A Stylized Binarization Procedure for Black/White Comics Using HSV Region Extension

Generally most of the black/white comics color in human's skin as white, while the dark region is filled with the irregular but regular patterns like hatching. Note that it is not enough for simple threshold method to perform this work. In this paper, we propose a simple and straightforward binarization procedure which can generate black/white comics from the video frame image. Our procedure is decoupled into two processes: region extension and binarization. First, the region extension based on mean shift segmentation is responsible to simplify and classify colors on the image. Second, we implement the dynamic binarization method to consider color information in HSV color model. Our novel black/white cartooning procedure was so successful to render comic cuts from a well-known cinema in a resonable time and manual intervention.