Image block matching based on GLCM (gray level co-occurence matrix) texture feature on grayscale image auto coloring

Abstract

Colorization is a coloring process in the image or video, which is done to provide detail and clarity to the image or video. This study used image gray scale to be colored by matching both color image pixel blocks and grayscale images based on GLCM texture feature (gray level co-occurance matrix) using a sum of absolute difference. Color image blocks are used as templates and grayscale image blocks as targets, searching for similarities between two image blocks by subtracting both GLCM texture feature values and comparing the target of GLCM value with the template value to obtain the smallest or near-zero value in the color block. The smallest in the color image block is a pair of grayscale image blocks, as both have similar features of the GLCM texture. Further, color of color image blocks are transferred to the grayscale block in accordance with the existing resemblance (pair), until all areas that have similarity are colored.