Abstract
With the development of economic globalization, more and more product designers are faced with the need of designing for customers from different countries. However, it is a challenge for designers to efficiently develop the desired mental images of certain products for target users with different cultural backgrounds. Our research proposed a deep learning-based system to facilitate designers to gain better awareness of the cross-culture differences between different target customers. We trained a kawaii classification neural network model with the data of 1414 cosmetic packaging images annotated by 12 Japanese females separately. As a follow-up investigation, we conducted neuron analysis to compare the features of kawaii packages perceived by Japanese participants with the results from a prior study conducted with Chinese participants. The result shows that Japanese females tended to see more girlish and exquisite design features as kawaii while Chinese females perceived more childish and round elements as kawaii. A reverse experiment further verified the effectiveness of adding these different design features to enhance Chinese or Japanese females’ perception of kawaii. We also noticed that it’s hard to obtain the cross-cultural differences in customers’ perception by extracting image parameters with a set of predefined visual features as such perception differences could be subconscious. Our deep learning-based Kansei design facilitation provides a feasible solution to customized design for target customers with different cultural backgrounds.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nagamachi, M.: Kansei engineering as a powerful consumer-oriented technology for product development. Appl. Ergon. 33, 289–294 (2002)
Yang, C.-C.: Constructing a hybrid kansei engineering system based on multiple affective responses: application to product form design. Comput. Ind. Eng. 60, 760–768 (2011)
Laohakangvalvit, T., Achalakul, T., Ohkura, M.: Kawaii feeling estimation by product attributes and Biological Signals. In: Proceedings of the 18th ACM International Conference on Multimodal Interaction (2016)
Ohkura, M., Komatsu, T., Aoto, T.: Kawaii rules: increasing affective value of industrial products. Indu. Appl. Affec. Eng. 97–110 (2014)
Matsubara, Y., Nagamachi, M.: Hybrid kansei engineering system and design support. Int. J. Ind. Ergon. 19, 81–92 (1997)
Nagamachi, M., Tachikawa, M., Imanishi, N., Ishizawa, T., Yano, S.: A successful statistical procedure on kansei engineering products. In: 11th QMOD Conference. In: Quality Management and Organizational Development Attaining Sustainability From Organizational Excellence to SustainAble Excellence, p. 22. Helsingborg, Sweden (2008)
Chen, J.-S., Wang, K.-C., Liang, J.-C.: A Hybrid Kansei Design Expert System Using Artificial Intelligence. In: Ho, T.-B., Zhou, Z.-H. (eds.) PRICAI 2008. LNCS (LNAI), vol. 5351, pp. 971–976. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-89197-0_93
Ohkura, M., Konuma, A., Murai, S., Aoto, T.: Systematic study for “Kawaii” products (the second report) -Comparison of “kawaii” colors and shapes -. In: 2008 SICE Annual Conference (2008)
Yang, C.-C.: A classification-based kansei engineering system for modeling consumers’ affective responses and analyzing product form features. Expert Syst. Appl. 38, 11382–11393 (2011)
Tsuchiya, T., Ishihara, S., Matsubara, Y., Nishino, T., Nagamachi, M.: A method for learning decision tree using genetic algorithm and its application to kansei engineering system. In: IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028) (1999)
Ishihara, S., Hatamoto, K., Nagamachi, M., Matsubara, Y.: Art1.5SSS for kansei engineering expert system. In: Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan) (1993)
Mitsuyo, M.: An application of image processing technology in Kansei Engineering. In: Prnc. 12th Triennial Congress of the International Ergonomics Association, pp. 123–126. Toronto (1994)
Ishihara, S., Ishihara, K., Nagamachi, M., Matsubara, Y.: An automatic builder for a kansei engineering expert system using self-organizing neural networks. Int. J. Ind. Ergon. 15, 13–24 (1995)
Li, Z., Tian, Z.G., Wang, J.W., Wang, W.M., Huang, G.Q.: Dynamic mapping of design elements and affective responses: A machine learning based method for affective design. J. Eng. Des. 29, 358–380 (2018)
Wang, K.-C.: A hybrid kansei engineering design expert system based on grey system theory and support vector regression. Expert Syst. Appl. 38, 8738–8750 (2011)
Ray, K.S., Ghoshal, J.: Neuro fuzzy approach to pattern recognition. Neural Netw. 10, 161–182 (1997)
Liu, S., Forrest, J., Yang, Y.: A brief introduction to grey systems theory. Grey Sys. Theo. Appl. 2, 89–104 (2012)
Gong, Y., Pei-Luen Patrick, R.: DL-KES: a deep learning based kansei engineering system. J. Japan Soc. Kansei Eng. 15, 29–31 (2017)
Cheok, A.D.: Kawaii: cute interactive media. In: Imagery in the 21st Century, pp. 245–265 (2011)
Ohkura, M., Goto, S., Higo, A., Aoto, T.: Relationship between kawaii feeling and biological signals. Trans. Japan Soc. Kansei Eng. 10, 109–114 (2011)
Laohakangvalvit, T., Achalakul, T., Ohkura, M.: Comparison on evaluation of Kawaiiness of cosmetic bottles between Japanese and Thai people. In: 2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII) (2019)
Laohakangvalvit, T., Achalakul, T., Ohkura, M.: Model of kawaii cosmetic bottle evaluations by Thai and Japanese. Kawaii Engineering, pp. 195–223 (2019)
Laohakangvalvit, T., Achalakul, T., Ohkura, M.: A method to obtain effective attributes for attractive cosmetic bottles by deep learning. Int. J. Affec. Eng. 19, 37–48 (2020)
Acknowledgments
We would like to thank all the Chinese and Japanese participants in our experiments. We really appreciate their valuable time and feedback on our research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, X., Rau, PL.P., Ohkura, M., Laohakangvalvit, T., Wang, B. (2022). A Deep Learning-Based Approach to Facilitate Cross-cultural Kansei Design. In: Rau, PL.P. (eds) Cross-Cultural Design. Interaction Design Across Cultures. HCII 2022. Lecture Notes in Computer Science, vol 13311. Springer, Cham. https://doi.org/10.1007/978-3-031-06038-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-06038-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06037-3
Online ISBN: 978-3-031-06038-0
eBook Packages: Computer ScienceComputer Science (R0)