Robust regression in computer vision

Doron Mintz

Research output: Contribution to journalConference article

Abstract

We describe the least median of squares (LMedS) robust estimator which identifies the surface corresponding to the absolute majority of the data points. However, when all the data points are corrupted by noise LMedS may fail. This is the case in computer vision applications, and we have developed a new approach which preserves the robustness of LMedS but avoids its artifacts in the presence of noise.

Original languageEnglish (US)
Pages (from-to)424-435
Number of pages12
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume1381
StatePublished - Jan 1 1991
Externally publishedYes
EventIntelligent Robots and Computer Vision IX: Algorithms and Techniques - Boston, MA, USA
Duration: Nov 5 1990Nov 7 1990

Fingerprint

Least Median of Squares
Robust Regression
computer vision
Computer Vision
Computer vision
regression analysis
Robust Estimators
estimators
artifacts
Robustness

All Science Journal Classification (ASJC) codes

  • Condensed Matter Physics
  • Electrical and Electronic Engineering

Cite this

@article{5f7f3d1cfc8d448d8a447813b4f95107,
title = "Robust regression in computer vision",
abstract = "We describe the least median of squares (LMedS) robust estimator which identifies the surface corresponding to the absolute majority of the data points. However, when all the data points are corrupted by noise LMedS may fail. This is the case in computer vision applications, and we have developed a new approach which preserves the robustness of LMedS but avoids its artifacts in the presence of noise.",
author = "Doron Mintz",
year = "1991",
month = "1",
day = "1",
language = "English (US)",
volume = "1381",
pages = "424--435",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

Robust regression in computer vision. / Mintz, Doron.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 1381, 01.01.1991, p. 424-435.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Robust regression in computer vision

AU - Mintz, Doron

PY - 1991/1/1

Y1 - 1991/1/1

N2 - We describe the least median of squares (LMedS) robust estimator which identifies the surface corresponding to the absolute majority of the data points. However, when all the data points are corrupted by noise LMedS may fail. This is the case in computer vision applications, and we have developed a new approach which preserves the robustness of LMedS but avoids its artifacts in the presence of noise.

AB - We describe the least median of squares (LMedS) robust estimator which identifies the surface corresponding to the absolute majority of the data points. However, when all the data points are corrupted by noise LMedS may fail. This is the case in computer vision applications, and we have developed a new approach which preserves the robustness of LMedS but avoids its artifacts in the presence of noise.

UR - http://www.scopus.com/inward/record.url?scp=0025796490&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025796490&partnerID=8YFLogxK

M3 - Conference article

VL - 1381

SP - 424

EP - 435

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -