Title: A Kansei retrieval method using physical features of Japanese crafts

Authors: Akihiro Miyakawa, Tomoyuki Ishida, Yoshitaka Shibata

Addresses: Information Policy Division, Nanao City Hall, 25 E-bu, Sodegae, Nanao, Ishikawa 926-8611, Japan. ' Graduate School of Software and Information Science, Iwate Prefectural University, 152-52 Sugo, Takizawa, Iwate 020-0193, Japan. ' Graduate School of Software and Information Science, Iwate Prefectural University, 152-52 Sugo, Takizawa, Iwate 020-0193, Japan

Abstract: In this paper, we propose a Kansei retrieval method based on the design pattern of traditional Japanese crafts to provide a user with the desired presentation space. The visual quantitative features for crafts are extracted using Visual Pattern Image Coding (VPIC) and registered in the multimedia database and the relation between Kansei words and the visual feature of crafts are analysed using the questionnaire. Then, the visual features are compared with the quantitative feature values. Through the above process, the relation between the design pattern components and edge types is found using VPIC. Finally the Kansei retrieval method can be realised.

Keywords: multimodal communication; tele-immersion; sensitivity information processing; ultra high speed networks; image retrieval; feature extraction; multimedia databases; Kansei; traditional crafts; Japanese crafts; Japan; design patterns; visual patterns; 3D computer graphics.

DOI: 10.1504/IJASS.2010.031554

International Journal of Applied Systemic Studies, 2010 Vol.3 No.1, pp.59 - 72

Published online: 10 Feb 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article