Machine learning for map interpretation: An intelligent tool for environmental planning

Esposito

Machine Learning and Data Mining in Pattern Recognition

et al. 2001

Abstract. Information given in topographic map legends or in GIS models is often insufficient to recognize interesting geographical patterns. Some prototypes of GIS have already been extended with a knowledge-base and some reasoning capabilities to support sophisticated map interpretation processes. Nevertheless, the acquisition of the necessary knowledge is still an open problem to which machine learning techniques can provide a solution. This paper presents an application of first-order rule induction to pattern recognition in topographic maps. Research issues related to the extraction of first-order logic descriptions from vectorized topographic maps are introduced. The recognition of morphological patterns in topographic maps of the Apulia region is presented as a case study.

“…It is easy to see that the classification rules are intelligible and meaningful. Some experimental results obtained in a previous work are reported in [8].…”

Section: The Recognition Of Morphological Patterns In Topographic Mapmentioning

confidence: 99%

Section: Feature Extraction From Vectorized Topographic Mapsmentioning

confidence: 99%

See 1 more Smart Citation

First-Order Rule Induction for the Recognition of Morphological Patterns in Topographic Maps

Esposito

Machine Learning and Data Mining in Pattern Recognition

et al. 2001

“…Few works on feature extraction from vectorized maps are reported in the literature [2] and they refer only to cadastral maps. The first application of feature extraction algorithms to vectorized topographic maps can be found in the work by Esposito et al [4]. For environmental planning tasks, fifteen features were specified with the help of domain experts (see Table 1).…”

Section: Generating Logic Descriptions Of Map Cellsmentioning

confidence: 99%

“…As to the former issue, the contribution of experts interested in automating the identification of some morphological elements in topographic maps is crucial. In a previous work [4], the collaboration of experts in geomorphology and territory planning allowed us to define a sufficiently general set of relevant features, which are used by humans in their map interpretation process.…”

Section: Introductionmentioning

confidence: 99%

Generating Logic Descriptions for the Automated Interpretation of Topographic Maps

Lecture Notes in Computer Science

Lisi

et al. 2002

Self Cite

Abstract. Automating the interpretation of a map in order to locate some geographical objects and their relations is a challenging task, which goes beyond the transformation of map images into a vectorized representation and the recognition of symbols. In this work, we present an approach to the automated interpretation of vectorized topographic maps. It is based on the generation of logic descriptions of maps and the application of symbolic Machine Learning tools to these descriptions. This paper focuses on the definition of computational methods for the generation of logic descriptions of map cells and briefly describes the use of these logic descriptions in an inductive learning task.

Discovering Geographic Knowledge: The INGENS System

Esposito

Lecture Notes in Computer Science

et al. 2000

INGENS is a prototypical GIS which integrates machine learning tools in order to discover geographic knowledge useful for the task of topographic map interpretation. It embeds ATRE, a novel learning system that can induce recursive logic theories from a set of training examples. An application to the problem of recognizing four morphological elements in topographic maps of the Apulia region is also illustrated