Premium
Recognition and Classification of Urban Shapes
Author(s) -
Medda Francesco,
Nijkamp Peter,
Rietveld Piet
Publication year - 1998
Publication title -
geographical analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.773
H-Index - 65
eISSN - 1538-4632
pISSN - 0016-7363
DOI - 10.1111/j.1538-4632.1998.tb00404.x
Subject(s) - computer science , index (typography) , contrast (vision) , artificial intelligence , pattern recognition (psychology) , geometric shape , shape analysis (program analysis) , mathematics , geometry , static analysis , world wide web , programming language
This paper is concerned with a methodology that is able to recognize and classify geometric shapes, in particular urban shapes. The main objective of this study is to develop a shape index that will address Whyte's category of “spatial form” (1968), that is, the external appearance or outward form, in contrast with the “internal form,” which is the structural form. We first review methodologies of shape recognition and classification. Next, we propose a viable formulation for such an endeavor by drawing from the aforementioned methodologies, and we aim to overcome some of their limitations by formulating a new index. We will apply the resulting shape index to an illustrative case in order to recognize urban shapes.