Automatically assigned DDC number: 621367

Manually assigned DDC number: 00642

Number of references: 0

Title: A Legend-Driven Geographic Symbol Recognition System

Author:

Author:

Subject: Hanan Samet,Aya Soffer A Legend-Driven Geographic Symbol Recognition System

Description: The problem of converting paper maps into digital formats is a major concern today with the emergence of geographical information systems (GIS) as replacements of the traditional paper map. One of the major problems in this conversion is that a paper map is nothing more than an abstraction. The information found in maps is mainly symbolic rather than an accurate graphical description of the region covered by the map. A system is presented that utilizes the symbolic knowledge found in the legend of the map to drive geographic symbol recognition. The geographic symbol layer(s) of the map are first scanned. The legend of the map is located and segmented. The geographic symbols are identified, and their semantic meaning is attached to them. This information is used to build an initial training set that is then used to classify geographical symbols in input maps using statistical pattern recognition. User interaction is required at first to assist in building the training set to account for...

Contributor: The Pennsylvania State University CiteSeer Archives

Publisher: unknown

Date: 1998-10-23

Pubyear: 1994

Format: ps

Identifier: http://citeseer.ist.psu.edu/140513.html

Source: http://www.cs.umd.edu/~hjs/pubs/icpr94_ieee.ps.gz

Language: en

Rights: unrestricted