Generation of Photo-Mosaic Images through Block Matching and Color Adjustment

Authors: Hae-Yeoun Lee

Abstract:

Mosaic refers to a technique that makes image by gathering lots of small materials in various colors. This paper presents an automatic algorithm that makes the photo-mosaic image using photos. The algorithm is composed of 4 steps: partition and feature extraction, block matching, redundancy removal and color adjustment. The input image is partitioned in the small block to extract feature. Each block is matched to find similar photo in database by comparing similarity with Euclidean difference between blocks. The intensity of the block is adjusted to enhance the similarity of image by replacing the value of light and darkness with that of relevant block. Further, the quality of image is improved by minimizing the redundancy of tiles in the adjacent blocks. Experimental results support that the proposed algorithm is excellent in quantitative analysis and qualitative analysis.

Keywords: Photo-mosaic, Euclidean distance, Block matching, Intensity adjustment.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1337093

References:

[1] Wikipedia, Mosaic, http://en.wikipedia.org/wiki/Mosaic
[2] S. Battiato, G. Di Blasi, G. M. Farinella, and G. Gallo, "A Survey of Digital Mosaic Techniques,” Proc. of Eurographics Italian Chapter Conference, 2006, pp. 129-135.
[3] R. Silvers and M. Hawley, "Photomosaics,” Henry Holt and Co., Inc. New York, 1997.
[4] A. W. Klein, T. Grant, A. Finkelstein, and M. F. Cohen, "Video Mosaics,” Proc. of International Symposium on Non Photorealistic Rendering, 2002, pp. 21-28.
[5] G. Di Blasi and M. Petralia, "Fast Photomosaic,” Proc. of International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, 2005.
[6] The official web site of AndreaMosaic, http://www.andreaplanet. com/andreamosaic/