Contour Junction Extraction.

作者: Robert Bergevin , Marielle Mokhtari

DOI:

关键词: Artificial intelligenceComputer visionPlanarImage (mathematics)Phase (waves)Constant curvatureImperfectComputer science

摘要: This paper introduces an intermediate grouping phase whereby structures, meant to correspond generic 3D junctions of planar and curved surfaces, are extracted from imperfect basic constant curvature contour primitives. research work is part a more project for detecting describing high-level structures corresponding objects and/or parts in single illuminance image cluttered scene. MAGNO (Multi-level Access Generic Notable Objects), computer vision system exploiting constraints at each its hierarchical processing levels the heart project.

参考文章(4)
J Matas, J Kittler, Junction detection using probabilistic relaxation british machine vision conference. ,vol. 11, pp. 197- 202 ,(1993) , 10.1016/0262-8856(93)90036-G
A. Etemadi, J.-P. Schmidt, G. Matas, J. Illingworth, J. Kittler, Low-level Grouping of Straight Line Segments british machine vision conference. pp. 118- 126 ,(1991) , 10.1007/978-1-4471-1921-0_16
C. Fuchs, W. Forstner, Polymorphic grouping for image segmentation Proceedings of IEEE International Conference on Computer Vision. pp. 175- 182 ,(1995) , 10.1109/ICCV.1995.466789