A Graph-based approach for Kite recognition

• Published in: Pattern recognition letters Vol. 87; pp. 186 - 194
• Main Authors: Madi, Kamel, Seba, Hamida, Kheddouci, Hamamache, Barge, Olivier
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.02.2017; Elsevier Science Ltd; Elsevier
• Subjects: Artificial satellites; Computational mathematics; Computer Science; Computer Vision and Pattern Recognition; Data Structures and Algorithms; Datasets; Discrete Mathematics; Geographical distribution; Graph edit distance; Graph matching; Graph-based image modeling; Graphical representations; Graphs; Historical structures; Identification methods; Image Processing; Kite recognition; Kites; Object recognition; Operations Research; Pattern recognition; Satellite image; Satellite imagery; Satellite image; Kite recognition; Graph-based image modeling; Pattern recognition; Graph edit distance; Graph matching; Graph Edit distance
• DOI: 10.1016/j.patrec.2016.05.005
• ISSN: 0167-8655

•We propose a complete graph-based process for Kite recognition.•We propose a geometric hierarchical graph matching solution to the problem of geometric graph matching.•We also propose a benchmark of Kite graphs from real images.•We experimentally evaluate our approach over both real and synthetic data sets. [Display omitted] Kites are huge archaeological structures of stone visible from satellite images. Because of their important number and their wide geographical distribution, automatic recognition of these structures on images is an important step towards understanding these enigmatic remnants. This paper presents a complete identification tool relying on a graph representation of the Kites. As Kites are naturally represented by graphs, graph matching methods are thus the main building blocks in the Kite identification process. However, Kite graphs are disconnected geometric graphs for which traditional graph matching methods are useless. To address this issue, we propose a graph similarity measure adapted for Kite graphs. The proposed approach combines graph invariants with a geometric graph edit distance computation leading to an efficient Kite identification process. We analyze the time complexity of the proposed algorithms and conduct extensive experiments both on real and synthetic Kite graph data sets to attest the effectiveness of the approach. We also perform a set of experimentations on other data sets in order to show that the proposed approach is extensible and quite general.