Composing photomosaic images using clustering based evolutionary programming

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

3 Scopus Citations
View graph of relations

Related Research Unit(s)


Original languageEnglish
Pages (from-to)25919–25936
Journal / PublicationMultimedia Tools and Applications
Issue number18
Online published3 Jun 2019
Publication statusPublished - Sep 2019


Photomosaic images are a type of images consisting of various tiny images. In the past, many approaches have been proposed trying to automatically compose photomosaic images. To obtain a better visual sense and satisfy some commercial requirements, a constraint that a tiny image should not be repeatedly used many times is usually added. With the constraint, algorithms using greedy mechanism fail to solve it. In this paper, we present an approach called clustering based evolutionary programming to deal with the problem. Our new approach has a similar mechanism to that of evolutionary programming (we adopt mutation, selection and fitness evaluation) and uses the normalized color histogram information as the prior information. The two characteristics make our approach converges fast and performs well. In our experiment, the proposed algorithm is compared with the state of the art algorithms and software. The results indicate that our algorithm is able to generate higher quality photomosaic images.

Research Area(s)

  • Combinatorial optimization, Evolutionary algorithm, Evolutionary programming, Photomosaic