Colorization Algorithm for Monochrome Video by Sowing Color Seeds

Abstract

Recently, the study of the colorization algorithm for monochrome still images has prospered. Considering actual applications, an extension to monochrome video becomes important. This paper proposes two colorization algorithms for monochrome image sequence without scene changing in video. In our approach, key frames in the image sequence are firstly colorized by a conventional colorization technique for still image. In the technique, a small number of color seeds are sown on the monochrome key frame, and color seeds are propagated spatially to remaining monochrome pixels. Then, each color in the colorized frame propagates to the next monochrome frame by extracting a displacement vector for each pixel between two frames. In this paper, the displacement vector is calculated by a simple block-matching algorithm, and color propagation to temporary direction is performed. So, in the proposed algorithm, video colorization can be realized by setting only some color seeds on key frames. Experimental results suggest a success of colorization for video by setting key frames for each 10 frames.