Browse > Article
http://dx.doi.org/10.6109/jkiice.2019.23.8.896

An Effective Method for Generating Images Using Genetic Algorithm  

Cha, Joo Hyoung (Division of Creative Software Eng., Dong-eui University)
Woo, Young Woon (Division of Creative Software Eng., Dong-eui University)
Lee, Imgeun (Division of Digital Contents & Game Animation, Dong-eui University)
Abstract
In this paper, we proposed two methods to automatically generate color images similar to existing images using genetic algorithms. Experiments were performed on two different sizes($256{\times}256$, $512{\times}512$) of gray and color images using each of the proposed methods. Experimental results show that there are significant differences in the evolutionary performance of each technique in genetic modeling for image generation. In the results, evolving the whole image into sub-images evolves much more effective than modeling and evolving it into a single gene, and the generated images are much more sophisticated. Therefore, we could find that gene modeling, selection method, crossover method and mutation rate, should be carefully decided in order to generate an image similar to the existing image in the future, or to learn quickly and naturally to generate an image synthesized from different images.
Keywords
Genetic algorithm; Image generation; Gene modeling; Image synthesis;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 J. Soderlund and A. Blair, "Adversarial Image Generation Using Evolution and Deep Learning," 2018 IEEE Congress on Evolutionary Computation (CEC), pp.1-8, Jul. 2018.
2 K. Sims, "Artificial Evolution for Computer Graphics," Computer Graphics, vol. 25, no. 4, pp. 319-328, Jul. 1991.   DOI
3 T. Cook, "Gauguin: Generating Art Using Genetic Algorithms & User Input Naturally," Honors Theses, Paper 270, 2007 [Internet]. Available: https://digitalcommons.colby.edu/honorstheses/270/.
4 AI Dev [Internet]. Available: http://aidev.co.kr/index.php?mid=genetic&page=1&document_srl=413.
5 C. M. Mun, "Solving the test resource allocation using variable group genetic algorithm," Journal of the Korea Institute Of Information and Communication Engineering, vol. 20, no. 8, pp. 1415-1421, 2016.   DOI
6 Mona Lisa approximated with 150 circles through hill climbing genetic algorithm [Internet]. Available: https://www.youtube.com/watch?v=rGt3iMAJVT8.
7 Evolving Darwin - Genetic Algorithm [Internet]. Available: https://www.youtube.com/watch?v=dO05XcXLxGs.
8 Mona Lisa from 1500 characters with genetic algorithm [Internet]. Available: https://www.youtube.com/watch?v=TManzvC9pi8.
9 J. S. Byun, J. Kang, D. H. Yang and K. H. Lee, "On the Security of Image-based CAPTCHA using Multi-image Composition," Journal of The Korea Institute of Information Security and Cryptology, vol. 22, no.4, pp.761-770, Aug. 2012.
10 Image Evolution - Generating Image using Genetic Algorithm [Internet]. Available: https://www.youtube.com/watch?v=Tza09kC6Xnc.
11 Mona Lisa Approximation with 50 polygons using genetic algorithm [Internet]. Available: https://www.youtube.com/watch?v=Yz9MuI-tkiw.
12 Reproduce image with genetic algorithm [Internet]. Available: https://www.youtube.com/watch?v=iV-hah6xs2A.
13 Genetic Algorithm [Internet]. Available: https://www.youtube.com/watch?v=5ZF_VdWMXKY.
14 GAraw Image Based Genetic Algorithm [Internet]. Available: https://www.youtube.com/watch?v=FtLE309IpK8.
15 Fitness proportionate selection [Internet]. Available: https://en.wikipedia.org/wiki/Fitness_proportionate_selection.