Design of Japanese Kimono (Yukata) using an Interactive Genetic Algorithm
Maiko SUGAHARA* Mitsunori MIKI** and Tomoyuki HIROYASU***
(Received January 20, 2009)
In recent years, the design of yukata changed from the fixed traditional designs to various designs. People are interested in the design of yukata. It is useful to design a yukata suitable for each preference. But, in many cases, people have ambiguous image for their favorite yukata, it is difficult to make their favorite design. We propose a yukata design system using an Interactive Genetic Algorithm (IGA). The proposed system is for designing a yukata to suit user’s taste. From the assessment experiment of the system, it was found that the proposed system proved to be effective in the designing of a yukata. In addition, we proposed additional functions that allow obi (sash) color mutation partially in search for the solution. And the experimental results showed the effectiveness of the additional functions.
Key words Optimization, Interactive Genetic Algorithm, Yukata design system, Color combination
1.
* Graduate Student, Department of Knowledge Engineering and Computer Sciences, Doshisha University, Kyoto Telephone:+81-774-65-6924, Fax:+81-774-65-6716, E-mail:msugahara@mikilab.doshisha.ac.jp
** Department of Knowledge Engineering and Computer Sciences, Doshisha University, Kyoto Telephone:+81-774-65-6930, Fax:+81-774-65-6716, E-mail:mmiki@mail.doshisha.ac.jp
*** Faculty of Life and Medical Sciences,Doshisha University, Kyoto
Telephone:+81-774-65-6932, Fax:+81-774-65-6019, E-mail:tomo@is.doshisha.ac.jp 1, 2)
Interactive Genetic Algorithm IGA 3) IGA
3-D CG 4),
5) 6)
IGA
IGA
IGA
2.
User Display System
Evaluate
GA Alternative solutions
Fig. 1. IGA system.
3. IGA 3.1
• 3
3
2 24
• RGB HSB
HSB 8)
HSB 3
0 360
100 0
• 1 1
Fig. 2 HSB
HSB
0 1
0 1 0 1
Fig. 2
0 1 2 3 4 5 6 7 8 9
Yukata
fabric Obi Pattern
H S B H S B H S B
Pattern number gene
number㧦 10
Yukata fabric number
(0:plane,1:stripe) (0-23) Individual Obi
Pattern Yukata fabric
1㧦 0㧦
̖ 23㧦
Fig. 2. Chromosome.
3.2
IGA Fig.
3 Fig. 3
Generation of first individual
Evaluation
Selection Crossover Mutation
Start
End Yes
No
Human Operation
Terminal Criterion Display
Fig. 3. Flow chart of yukata design system.
•
Fig. 4
Select favorite design
Fig. 4. Userinterface for selection of first Individu- als.
•
12 Fig. 5
Continue seach button
End seach button Generation count
Evaluation tool
* Button
* Slider bar
Fig. 5. Example of display.
•
5
IGA
•
•
n n
n=2
12 12
•
BLX-α9) BLX-α
2 α
0
Fig. 6.
Fig. 6. A
B
BLX-α
Range of generating offsprings
B
ParentA
ParentB 㱍d
d
㱍d
Example of a crossover for kimono fabric's Hue.
Offspring
Offspring ParentA
ParentB
Fig. 6. Example of crossover.
•
20 22
1. 1
2. 2
4.2
Fig. 7 Fig. 7
8
5%
9%
86%
What kind of yukata do you imagine wearing (imagine a girl wearing) to a fireworks show?
How much can you imagine it?
Clear image
Can somewhat imagine and express in words Cannot express in words but can somewhat imagine Can't imagine at all
Fig. 8. Result of questionnaire item 1.
2 Fig. 9
Fig. 9
5% 5%
23%
67%
Yes
Somewhat designed it Can㵭t really say Couldn㵭t really design it No
Were you able to design a yukata that fitted your design concept with this system?
Fig. 9. Result of questionnaire item 2.
5.
5.1 4.2
•
•
Fig. 10
Change the color of obi
Change the obi color of only individuals that were stochastically selected.
Fig. 10. User interface after action of the button.
1.
2.
1
1
1
4.2
2
0.3 2 3
1
4.1 20 22
4.1
• 3
• 4
5.2
3 Fig. 11
Fig. 11
64%
Were you able to design a yukata that fitted the concept by using the obi color mutation
Couldn㵭t really design it No
Fig. 11. Result of questionnaire item 3.
9%
5%
9%
59%
18%
Which of the two systems (the basic and the improved) did you find easier to design a yukata that fitted the concept better with?
Improved system Preferred improved system Can't really say
Preferred basic system Basic system
Fig. 12. Result of questionnaire item 4.
Fig. 13 Fig. 13
13
•
Fig. 13 1 2
Before After Final design
Elite individual Mutation individual Subject 2
Subject 3
Fig. 13. Example of yukata by using improved sys- tem.
•
6.
IGA
1
1) T. Sano, H. Ukida, H. Yamamoto. Adaptive texture alignment for japanese kimono design.
Proceedings of the IEEE Instrumentation and Measurement Technology Conference, Vol. 2, pp.
pp.1307–1310, 2005.
2) T. Sano, H. Nagahata, H. Yamamoto. Design support system for japanese kimono. IECON’98 Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society, Vol. 1, pp.
199–104, 1998.
3) , , .
4. , pp.
325–361, 2000.
4) K. Aoki and H Takagi. 3-D CG Lighting with an Interactive GA. 1st Int’l Conf. on Conven- tional and Knowlidge-based Intelligent Electronic Systems, pp. 296–301, 1997.
5) H.-S. Kim and S.-B. Application of interactive genetic algorithm to fashion design. Engineer- ing Applications of Artificial Intelligence 13(6), Vol. 1, pp. 635–644, 2000.
6) , , , ,
, .
.
, Vol. 10, No. 2, pp. 113–122, 2008.
8) , .
. , 2004.
9) L.J Eshleman and J.D Schaffer. Real-Coded Ge- netic Algorithms and Interval-Schemata.Founda- tions of Genetic Algorithms, Vol. 2, pp. 187–202, 1993.
Select favorite design
Fig. 4. Userinterface for selection of first Individuals
Continue seach button
End seach button Generation count
Evaluation tool
* Button
* Slider bar
Fig. 5. Example of display
B
ParentA
ParentB 㱍d
d
Example of a crossover for kimono fabric's Hue.
Offspring
Offspring ParentA
Fig. 7. Example of final design
Change the color of obi
Change the obi color of only individuals that were stochastically selected.
Fig. 10. User interface after action of the button
Subject 1
Before After Final
design
Elite individual Mutation individual Subject 2
Subject 3