Logistic regression for feature selection and soft classification of remote sensing data

Qi Cheng, Pramod K. Varshney, Manoj K. Arora

Research output: Contribution to journalArticlepeer-review

60 Scopus citations

Abstract

Feature selection is a key task in remote sensing data processing, particularly in case of classification from hyperspectral images. A logistic regression (LR) model may be used to predict the probabilities of the classes on the basis of the input features, after ranking them according to their relative importance. In this letter, the LR model is applied for both the feature selection and the classification of remotely sensed images, where more informative soft classifications are produced naturally. The results indicate that, with fewer restrictive assumptions, the LR model is able to reduce the features substantially without any significant decrease in the classification accuracy of both the soft and hard classifications.

Original languageEnglish (US)
Article number1715302
Pages (from-to)491-494
Number of pages4
JournalIEEE Geoscience and Remote Sensing Letters
Volume3
Issue number4
DOIs
StatePublished - Oct 1 2006

Keywords

  • Feature selection
  • Linear discriminant analysis (LDA)
  • Logistic regression (LR)
  • Soft classification

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Logistic regression for feature selection and soft classification of remote sensing data'. Together they form a unique fingerprint.

Cite this