An aesthetic mosaic image construction in a controllable manner

Abstract

Image-based mosaic is a technique which transfers cells of a target image with a group of tile images preserving the whole appearance of the target image. A typical mosaic algorithm includes cell partition and search of a large database for tile images which looks most similar to the cell images. In this paper, a target image is partitioned into different-sized cells with a QuadTree method and then tile images from a small SelfOrganizing Map clustered database is selected to fill the cells. The cell partition and tile image selection are processed in a controllable manner to generate different mosaics and variants without losing aesthetic effect.

A Natural Image Pointillism with Controlled Ellipse Dots

“…As the most prevalent form of IBAR [1], SBR algorithm renders a 2D image with atomic primitives to simulate a particular style in a local or global manner. The primitives involved in SBR are virtual painting brush [2,3], tiles [4], points (stippling, Halftoning, and hatching) [5][6][7][8][9][10][11][12][13], and even images [14][15][16][17]. Some also simulated water-color style [18], pencil and ink style [19,20], line drawing [21,22], and Pointillism [23][24][25][26][27].…”