Robust correspondence recognition for computer vision

Radim Šára ()
Additional contact information
Radim Šára: Czech Technical University, Center for Machine Perception, Department of Cybernetics

A chapter in Compstat 2006 - Proceedings in Computational Statistics, 2006, pp 119-131 from Springer

Abstract: Abstract In this paper we introduce constraint satisfaction framework suitable for the task of finding correspondences in computer vision. This task lies in the heart of many problems like stereovision, 3D model reconstruction, image stitching, camera autocalibration, recognition and image retrieval and a host of others. If the problem domain is general enough, the correspondence problem can seldom employ any well-structured prior knowledge. This leads to tasks that have to find maximum cardinality solutions satisfying some weak optimality condition and a set of constraints. To avoid artifacts, robustness is required to cope with decision under occlusion, uncertainty or insufficiency of data and local violations of prior model. The proposed framework is based on a robust modification of graph-theoretic notion known as digraph kernel.

Keywords: Computer Vision; Correspondence Problem; Matching; Robustness; Digraph Kernel (search for similar items in EconPapers)
Date: 2006
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-7908-1709-6_10

Ordering information: This item can be ordered from
http://www.springer.com/9783790817096

DOI: 10.1007/978-3-7908-1709-6_10

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().