A FEATURE EXTRACTION METHOD FOR RETRIEVING TRADITIONAL JAPANESE CRAFTING OBJECTS

DOI

抄録

In this paper, we propose a Kansei Retrieval Method (KRM) based on the design pattern of Traditional Japanese Crafting Objects (TJCO). Our method provides users with the desired presentation space in Digital Traditional Japanese Crafting System (DTJCS). The DTJCS is a virtual reality presentation system of traditional Japanese crafting for both classic and modern fittings. The KRM is a retrieval method based on user feelings. The visual quantitative feature values are extracted by using Visual Pattern Image Coding (VPIC). These values include the total number, the frequency rate, the dispersion rate and the deviation rate for different edges. The quantitative feature values for TJCO are registered in the multimedia database and the relation between Kansei words and the sensitive feature of TJCO are analyzed by using a questionnaire. Then, the sensitive features are compared with the quantitative feature values. Through the above process and using VPIC, we can find the relation between the design pattern components and edge types. We implemented the VPIC system and evaluated its performance by experiment. The experimental results show the effectiveness of our proposed method.

収録刊行物

詳細情報 詳細情報について

  • CRID
    1390282679459455488
  • NII論文ID
    130004301697
  • DOI
    10.5057/kei.5.3_15
  • ISSN
    18845231
    13451928
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • Crossref
    • CiNii Articles
  • 抄録ライセンスフラグ
    使用不可

問題の指摘

ページトップへ