A Parallel Genetic Algorithm for Creating Virtual Portraits of Historical Figures

• Autorzy: Krawczyk H. , Proficz J. , Ziółkowski T.
• Języki publikacji: EN

Abstrakty

EN

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.

Słowa kluczowe

EN

genetic algorithms; fitness function; KASKADA platform; parallel processing; high performance computing

• Wydawca: Politechnika Gdańska
• Czasopismo: TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk
• Rocznik: 2012
• Tom: Vol. 16, No 1-2
• Strony: 145--162
• Opis fizyczny: Bibliogr. 21 poz., rys., tab.

Twórcy

autor

Krawczyk H.

autor

Proficz J.

autor

Ziółkowski T.

• Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, Narutowicza 11/12, 80-233 Gdansk, Poland,

Bibliografia

• [1] Whitely D 1993 A Genetic Algorithm Tutorial, Technical Report CS-93-103, Colorado State University
• [2] Konak A, Coit D W and Smith A E 2006 Reliability Engineering & System Safety, Genetic Algorithms and Reliability 91 (9) 992
• [3] ¨Ozyer T, Liu Y, Alhajj R and Barker K 2004 Proc. Third Int. Conf. Advances in Information Systems, ADVIS’04, Springer-Verlag Berlin, Heidelberg, pp. 451–461
• [4] Bevilacqua V, Pacelli V and Saladino S 2011 Proc. 7 th Int. Conf. Advanced Intelligent Computing, ICIC’11, Springer-Verlag Berlin, Heidelberg, pp. 186–193
• [5] Mishra B S P, Addy A K, Roy R and Dehuri S 2011 Proc. Int. Conf. on Communication, Computing & Security, ICCCS’11, ACM New York, USA, pp. 409–414
• [6] Toffolo A and Benini E 2003 Evolutionary Computation 11 (2) 151
• [7] Linton R C 2004 Proc. 42 nd Annual Southeast Regional Conf., ACM-SE 42, ACM New York, USA
• [8] Turk M and Pentland A 1991 J. Cognitive Neuroscience 3 (1) 71
• [9] Lee Y H, Han C W and Kim T S 2006 Proc. 6 th Int. Conf. on Computational Science, ICCS’06, Springer-Verlag Berlin, Heidelberg, IV, pp. 862–869
• [10] Wolberg G 1998 Visual Computer 14 360
• [11] Zhang Z, Wang L, Guo B and Shum H Y 2002 Trans. on Graphics, Proc. ACM SIG-GRAPH, ACM New York, USA, 21 (3) 457
• [12] Kekre H B, Sarode T K and Patil S M 2011 Proc. Int. Conf. & Workshop on Emerging Trends in Technology, ICWET’11, ACM New York, USA, pp. 357–362
• [13] Bookstein F L 1989 IEEE Transactions on Pattern Analysis and Machine Intelligence 11 (6) 567
• [14] Cantu-Paz E 1998 Genetic Programming, Madison, USA, pp. 455
• [15] Eklund S E 2004 Parallel Computing 30 (5-6) 647
• [16] Krawczyk H and Proficz J 2012 Interactive Multimedia, InTech, Croatia, pp. 289–312
• [17] Krawczyk H and Proficz J 2010 Proc. Int. Conf. on Signal Processing and Multimedia Applications, SIGMAP, SciTePress, Athens, Greece, pp. 26–31
• [18] CI TASK 2012 Galera Plus, http://www.task.gda.pl/kdm/kdm/gplus
• [19] Jordan H F and Alaghband G 2003 Fundamentals of Parallel Processing, Prentice Hall, Upper Saddle River, USA
• [20] Sun X H and Chen Y 2010 J. Parallel and Distributed Computing 70 (2) 183
• [21] Marr D T, Binns F Hill D L, Hinton G, Koufaty D A, Miller J A and Upton M 2002 Intel Technology J. 6 (1) 4