- Tytuł:
- A parallel genetic algorithm for creating virtual portraits of historical figures
- Autorzy:
-
Krawczyk, H.
Proficz, J.
Ziółkowski, T. - Powiązania:
- https://bibliotekanauki.pl/articles/1933983.pdf
- Data publikacji:
- 2012
- Wydawca:
- Politechnika Gdańska
- Tematy:
-
genetic algorithms
fitness function
KASKADA platform
parallel processing
high performance computing - Opis:
- In this paper we present a genetic algorithm (GA) for creating hypothetical virtual portraits of historical figures and other individuals whose facial appearance is unknown. Our algorithm uses existing portraits of random people from a specific historical period and social background to evolve a set of face images potentially resembling the person whose image is to be found. We then use portraits of the person’s relatives to judge which of the evolved images are most likely to resemble his/her actual appearance. Unlike typical GAs, our algorithm uses a new supervised form of fitness function which itself is affected by the evolution process. Additional description of requested facial features can be provided to further influence the final solution (i.e. the virtual portrait). We present an example of a virtual portrait created by our algorithm. Finally, the performance of a parallel implementation developed for the KASKADA platform is presented and evaluated.
- Źródło:
-
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk; 2012, 16, 1-2; 145-162
1428-6394 - Pojawia się w:
- TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk
- Dostawca treści:
- Biblioteka Nauki
Artykuł