Abstract
Large datasets are generally required for machine learning. In order to improve the efficiency of the system, our team proposes a new Kansei modeling method, which requires users to collect only a small dataset. Using our method, the small datasets can search and collect large datasets classified in detail. As a result, our method creates the well-tuned Kansei model only from small datasets without the trouble of collecting many datasets.
Chapter PDF
Similar content being viewed by others
References
Tada, M., Kato, S.: Analysis and study of visual impressions using SVM and the application to automatic image classification. Technical Report of The Institute of Electronics, Information and communication Engineers 104(573) (20050114), 45–50 (2004)
Tada, M., Kato, S.: Analysis of characteristics of similar visual impressions and modeling of visual sensitivity. Thesis Report of The Institute of Electronics, Information and communication Engineers D-II J87-D-II(10), 1983–1995 (2004)
Chichiiwa, H.: Viewing colors by mind? Color psychology design., Fukumura Shuppan Inc.
Shigematsu, R., Kato, T.: Learning Efficiency with Automatic Classification of Teaching Data – Using Global Graphic Features and Structured Graphic Features. In: The 11th Proc. of Japan Society of Kansei Engineering,
Nanbu, F., Hachimura, K.: Image search system which automatically configure similar judgment criteria, Symposium on Human Science and Computer (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Uesaka, S., Yasukawa, K., Kato, T. (2011). Kansei Modeling on Visual Impression from Small Datasets. In: Stephanidis, C. (eds) HCI International 2011 – Posters’ Extended Abstracts. HCI 2011. Communications in Computer and Information Science, vol 173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22098-2_121
Download citation
DOI: https://doi.org/10.1007/978-3-642-22098-2_121
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22097-5
Online ISBN: 978-3-642-22098-2
eBook Packages: Computer ScienceComputer Science (R0)