A target recognition technique employing geometric invariants

Citation
Bs. Song et al., A target recognition technique employing geometric invariants, PATT RECOG, 33(3), 2000, pp. 413-425
Citations number
12
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
PATTERN RECOGNITION
ISSN journal
00313203 → ACNP
Volume
33
Issue
3
Year of publication
2000
Pages
413 - 425
Database
ISI
SICI code
0031-3203(200003)33:3<413:ATRTEG>2.0.ZU;2-W
Abstract
In this paper, we propose an efficient target recognition technique in the complex scenes. For the viewpoint invariant matching, the well-known geomet ric invariants, the invariants of five coplanar points and the invariants o f five coplanar lines. which are invariant under the projective transform, are employed. To alleviate the computational complexity, the circular order ed matching technique and compatibility test are proposed, utilizing the ge ometric properties. Moreover, stability of the invariants for five coplanar points to the input noise is analyzed, and a method to select the stable i nvariants is also suggested. The performance of the proposed algorithm is e valuated on both various synthetic and real images. The results of the expe riments show that the proposed matching technique is both effective and sta ble to the input noise for the target recognition in complex images. (C) 20 00 Pattern Recognition Society. Published by Elsevier Science Ltd. All righ ts reserved.