- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Spatial Indication Mechanism for Exploratory Information Retrieval in Multidimensional Space
-
- WATANABE Masahiro
- Graduate School of Information Science Nara Institute of Science and Technology (NAIST)
-
- YOSHIKAWA Masatoshi
- Graduate School of Information Science Nara Institute of Science and Technology (NAIST)
-
- UEMURA Shunsuke
- Graduate School of Information Science Nara Institute of Science and Technology (NAIST)
Bibliographic Information
- Other Title
-
- オブジェクトの相対位置関係に基づく検索要求の視覚的記述とその処理方法
Search this article
Description
In this paper, we propose a new approach to visual information retrieval. In this approach, first, an object-attribute matrix generated from an object set is decomposed using the Singular Value Decomposition(SVD) method. In the second step, users place "yardstick objects" by which they can specify the retrieval conditions in the 2D-space. And then, users can indicate a query object in the same 2D-space. The spatial relationships between the query object and "yardstick objects" are interpreted as the definition of the plane, or as the search conditions. Then the object information is visualized in a 2D-space using the result of SVD. With this approach, users can easily specify retrieval conditions which will be complicated when expressed in Boolean expressions of keywords. And relevant objects that do not contain the attribute be the query can be properly characterized and identified. Such visual method realizes smooth and effective interactions between the system and users.
Journal
-
- IPSJ SIG Notes
-
IPSJ SIG Notes 113 33-38, 1997-07-14
Information Processing Society of Japan (IPSJ)
- Tweet
Details 詳細情報について
-
- CRID
- 1571698602152671360
-
- NII Article ID
- 110002930618
-
- NII Book ID
- AN10112482
-
- ISSN
- 09196072
-
- Text Lang
- ja
-
- Data Source
-
- CiNii Articles