The Diverging Definition of Robustness in Statistics and Computer Vision

Peter Meer ()
Additional contact information
Peter Meer: Rutgers University, Department of Electrical Engineering

A chapter in Robust and Multivariate Statistical Methods, 2023, pp 395-406 from Springer

Abstract: Abstract Statistics and computer vision have a different role for robustness. Statisticians are primarily concerned with the theoretical properties of estimators when models are only approximately true. In computer vision, performance takes precedence over theoretical considerations. This divergence is exemplified in statistics by the robust M-estimator in contrast to the RANdom SAmple Consensus (RANSAC) and the Multiple Input Structures with Robust Estimator (MISRE) in computer vision. All three have defined algorithms, but the M-estimator is based on theoretical results, while RANSAC and MISRE only emphasize recovering significant inlier structures. I offer suggestions for how the theory of the M-estimator can be further applied to MISRE, or MISRE can be applied to M-estimator.

Keywords: Robustness; M-estimator; RANSAC; MISRE (search for similar items in EconPapers)
Date: 2023
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:978-3-031-22687-8_18

Ordering information: This item can be ordered from
http://www.springer.com/9783031226878

DOI: 10.1007/978-3-031-22687-8_18

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 ().