Colorization is the process of adding colors to monochrome images. In this paper we present a scribble-based colorization, which uses nearest neighborhood propagation and mixed weighing. The major assumption of our method is that chrominance is similar if luminance is similar in a natural image. We introduce the definition of the nearest neighborhood and mixed weighting. Non-local-mean-based patch weight and point weight are used in the mixed weighting. Experimental results show the benefits of our method.