Publisher: Maney Publishing
ISSN: 1743-2774
Source: The Cartographic Journal, Vol.43, Iss.2, 2006-07, pp. : 157-170
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
The generalization of area features is a very important topic in digital map generalization, particularly in thematic map generalization. The operations used in area generalization, will cause changes in the geometry and thematic attributes of area features and the topological relationships between them. Very limited quantitative measures, especially for semantics, are available to describe the effect of generalization when multiple objects are involved or when the entire map needs to be characterized. Therefore, the aim of this study is to provide some quantitative measures for the changes (especially in semantics) that have occurred during generalization. A set of quantitative measures of data quality, i.e. accuracy, consistency, and completeness, has been developed to assess such effects. The effect of generalization on area features are compared between two approaches, geometry-based merging and theme-based aggregation. An experimental test has also been carried out to illustrate their differences in terms of the proposed quality measures, which demonstrates the practical usefulness of these measures.
Related content
Flattening and Saturation: Two Representation Changes for Generalization
By Rouveirol C.
Machine Learning, Vol. 14, Iss. 2, 1994-02 ,pp. :
Estimating Generalization Error on Two-Class Datasets Using Out-of-Bag Estimates
By Bylander T.
Machine Learning, Vol. 48, Iss. 1-3, 2002-07 ,pp. :