Development of Automatic Recognition System for Topographic Map Symbol
Project/Area Number |
01850125
|
Research Category |
Grant-in-Aid for Developmental Scientific Research
|
Allocation Type | Single-year Grants |
Research Field |
交通工学・国土計画
|
Research Institution | University of Tsukuba |
Principal Investigator |
HOSHI Takashi Information Science and Electronics, Associate Professor, 電子・情報工学系, 助教授 (80026129)
|
Co-Investigator(Kenkyū-buntansha) |
IKEBE Yasuhiko Information Science and Electronics, Professor University of Tsukuba, 電子・情報工学系, 教授 (10114034)
|
Project Period (FY) |
1989 – 1991
|
Project Status |
Completed (Fiscal Year 1991)
|
Budget Amount *help |
¥7,600,000 (Direct Cost: ¥7,600,000)
Fiscal Year 1991: ¥2,100,000 (Direct Cost: ¥2,100,000)
Fiscal Year 1990: ¥2,800,000 (Direct Cost: ¥2,800,000)
Fiscal Year 1989: ¥2,700,000 (Direct Cost: ¥2,700,000)
|
Keywords | Geographic Information System / Map Symbol Recognition / Symbol Pattern Recognition / Imare Processing of Topographic Map / 地図情報抽出 / パタ-ン認識 / 地形図記号 / 記号認識 / 画像認識 / 地図記号 |
Research Abstract |
It is necessary to develop a system by which information included in maps is recognized individually in order to constitute the grographical information system (GIS). In this study map symbols which are symbolized in the map information are taken as basic symbols and extracted. Moreover their charcteristic quantities are researched and the main elements by which map symbols can be recognized are extracted from the elements to constitute the map symbols. The results obtained from the research described above can be concluded as follows : (1) From the standpoint to recognize the map symbols, the concept that one image constitutes one symbol is ruled out and the concept that multi-image constitutes one symbol is introduced here. (2) a^-j ten kinds of recognition elements are extracted when one image constitutes one sumbol, while w^-z four kinds of recognition elements are extracted when multi-image constitutes one symbol. (3) The criterion of classification can be decided by calculating the threshold and range of every element to recognize map symbols based on 14 kinds of recognition elements.
|
Report
(4 results)
Research Products
(27 results)