A Fully automated design of binary decision tree for land cover classification

Masanobu Yoshikawa, Hisakazu Shindo, Ryuei Nishii, Shojiro Tanaka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

A fully automated design method of binary decision tree is proposed for land cover classification of remote sensing data. The proposed method has the following features: (1) all possible binary combinations of identification classes are tested as splitting pattern of classes; (2) additional variables by linear combination of paired bands are applied in data segmentation; (3) Automatic Interaction Detector technique is utilized to divide the data set into binary tree nodes. Completely enumerated Landsat MSS data with land-cover data are used for the test of the method and classification accuracy. Our new method is compared with Bayesian discriminant classifier in terms of accuracy and training sample set sizes.

Original languageEnglish
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
Editors Anon
PublisherIEEE
Pages1921-1923
Number of pages3
Volume3
Publication statusPublished - 1995
Externally publishedYes
EventProceedings of the 1995 International Geoscience and Remote Sensing Symposium. Part 3 (of 3) - Firenze, Italy
Duration: Jul 10 1995Jul 14 1995

Other

OtherProceedings of the 1995 International Geoscience and Remote Sensing Symposium. Part 3 (of 3)
CityFirenze, Italy
Period7/10/957/14/95

All Science Journal Classification (ASJC) codes

  • Software
  • Geology

Fingerprint Dive into the research topics of 'A Fully automated design of binary decision tree for land cover classification'. Together they form a unique fingerprint.

Cite this