Published in

Springer, Lecture Notes in Computer Science, p. 118-127, 2015

DOI: 10.1007/978-3-319-18224-7_12

Links

Tools

Export citation

Search in Google Scholar

Kite Recognition by Means of Graph Matching

This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Red circle
Preprint: archiving forbidden
Orange circle
Postprint: archiving restricted
Red circle
Published version: archiving forbidden
Data provided by SHERPA/RoMEO

Abstract

Kites are remnants of long stone walls that outline the shape of a child’s kite. But the kites are huge, their big size makes them often clearly visible on high-resolution satellite images. Identified at first in the Near East, their area of distribution is getting larger and larger. This wide distribution gives new dimensions in the interpretation of these structures. Consequently, a large scale recognition of kites will help archeologists to understand the functionality of these enigmatic constructions. In this paper, we investigate how the satellite imagery can be exploited in this purpose using a graph representation of the kites. We propose a similarity measure and a kite identification process that can highlights the preservation state of the kites. We also construct from real images a benchmark of kite graphs that can be used by other researchers.