Segmentation of Mosaic Images based on Deformable Models using Genetic Algorithms

posted Oct 27, 2016, 1:39 AM by Eric Medvet   [ updated Jul 21, 2017, 4:58 AM ]
Preservation and restoration of ancient mosaics is a crucial activity for the perpetuation of cultural heritage of many countries. Such an activity is usually based on manual procedures which are typically lengthy and costly. Digital imaging technologies have a great potential in this important application domain, from a number of points of view including smaller costs and much broader functionalities. In this work, we propose a mosaic-oriented image segmentation algorithm aimed at identifying automatically the tiles composing a mosaic based solely on an image of the mosaic itself. Our proposal consists of a Genetic Algorithm, in which we represent each candidate segmentation with a set of quadrangles whose shapes and positions are modified during an evolutionary search based on multi-objective optimization. We evaluate our proposal in detail on a set of real mosaics which differ in age and style. The results are highly promising and in line with the current state-of-the-art.
Ċ
Eric Medvet,
Dec 6, 2016, 8:32 AM
Ċ
Eric Medvet,
Dec 6, 2016, 8:29 AM