Abstract
In this paper, we propose visualizing multi-dimensional distribution used in pattern recognition system and construct a visualization system for multi-dimensional space which stimulates intuitive and visual understanding of pattern distribution for the purpose of education. We treat the method of visualizing the multi-dimensional vector data of each character on the handwritten digit recognition system. By applying principal component analysis, the original vectors are converted into principal components and three components. Ellipsoids of equal probability for each category are derived and visualized in the three-dimensional space shown in the visualization system. As a result, the boundary surfaces of each distribution of categories can be seen easily in the reduced three-dimensional space in spite of the fact that visualized vectors distributions do not represent all of vectors data. In conclusion, learners of pattern recognition can be stimulated their interest in and comprehension of multi-dimensional distribution through using this system.
Chapter PDF
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
References
Fukunaga, K.: Statistical pattern recognition, 2nd edn. Academic Press, Inc., San Diego (1990)
Yamamoto, K., Yoshikawa, T., Furuhashi, T.: A proposal of visualization method for multi-dimensional data using fuzzy clustering based on multiple discriminant analysis. IEICE Trans. J88-D-II(6), 975–984 (2005) (in Japanese)
Mochizuki, D., Takeshita, T., Esaki, N.: Development of an educational character recognition system. In: Proceedings of Tokai-Section Joint Conference on Electrical and Related Engineering, ROMBUNNO.N2-5 (2010) (in Japanese)
Esaki, N., Hisada, R., Takeshita, T.: Educational mutidimensional pattern recognition system using principal component analysis. In: Abstracts of 5th International Symposium on Advances in Technology Educaiton, p. 119 (2011)
Tsuruoka, M.: Handwritten Kanji and Hiragana character recognition using weighted direction index histogram method. IEICE Trans. J70-D(7), 1390–1397 (1987) (in Japanese)
Jolliffe, I.T.: Principal Component Analysis, 2nd edn. Springer-Verlag New York, Inc. (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yamamoto, T., Esaki, N., Takeshita, T. (2013). Educational Character Recognition System Implementing an Interactive Visualization of Multi-dimensional Distribution. In: Stephanidis, C. (eds) HCI International 2013 - Posters’ Extended Abstracts. HCI 2013. Communications in Computer and Information Science, vol 374. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39476-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-39476-8_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39475-1
Online ISBN: 978-3-642-39476-8
eBook Packages: Computer ScienceComputer Science (R0)