Automatic photomosaic algorithm through adaptive tiling and block matching

Abstract

Mosaic refers to a technique that forms images by gathering several small materials in various colors. Because of the recent developments in digital imaging technology, photomosaic technologies that form images using photos are utilized. In this paper, we present an automatic computer algorithm that forms photomosaic images through adaptive tiling and block matching. A photo database stores photos called tiles for mosaic and their feature values. A photomosaic image is generated through separating the input image into blocks of a pre-set size, performing adaptive tiling by comparing the similarity between adjacent blocks, conducting block matching to find a similar tile in the photo database, and adjusting the intensity to enhance tile similarity within each image block. Furthermore, the quality of the photomosaic image is improved by minimizing tile redundancy in adjacent blocks and limiting the number of tiles used. In our experiment, the performance of the proposed algorithm is compared with that of Andrea mosaic, Mosaically, and Mozaika software packages. The results indicate that the proposed algorithm is excellent in quantitative and qualitative analyses.