Gray scale image colorization using normalized cross correlation

This article proposes a novel approach to colorize a gray scale image with the help of a reference color image given by the user which presumably contains suitable color information for the grayscale image. Normalized Cross Correlation is used to search suitable color information from reference color image to construct chrominance values for pixels in the grayscale image. The proposed method is applied in YCbCr color model on different natural images captured using standard camera. For performance measure initially color image were converted into a grayscale images and those images were colorized using the proposed method. Experimental result shows the effectiveness of the colorization method.