Unsupervised Segmentation of Multispectral Images Using Hierarchical Markov Random Fields

13 References
  • NOGAWA Tomohiro
    Kyushu Institute of Technology, Department of Electrical, Electronic and Computer Engineering
  • NODA Hideki
    Kyushu Institute of Technology, Department of Electrical, Electronic and Computer Engineering
  • SHIRAZI Mehdi N.
    Osaka Institute of Technology, Department of Information Processing
  • KAWAGUCHI Eiji
    Kyushu Institute of Technology, Department of Electrical, Electronic and Computer Engineering

Bibliographic Information

Other Title
  • 階層的MRFモデルを用いたマルチスペクトル画像の教師なしセグメンテーション

Search this article

Description

This paper proposes an Markov Random Field (MRF) model-based method for unsupervised segmentation of multispectral images, in which the intra-class correlation of multispectral data as well as the class label correlation are taken into account. In this method a set of multispectral images is modeled by a hierarchical MRF model. The proposed segmentation method is an iterative method composed of parameter estimation and segmentation which is based on the framework of the Expectation and Maximization (EM) method. Making use of an approximation for the Baum function in the expectation step, parameter estimation is reduced to the conventional Maximum Likelihood (ML) estimation given the current estimate of the hidden class label. The estimation of the class label, which corresponds to image segmentation, is carried out by a deterministic relaxation method proposed by us.

Journal

  • Technical report of IEICE. PRMU

    Technical report of IEICE. PRMU 96 (384), 45-52, 1996-11-21

    The Institute of Electronics, Information and Communication Engineers

References(13)*help

See more

Keywords

Details 詳細情報について

  • CRID
    1572824502300276608
  • NII Article ID
    110003274567
  • NII Book ID
    AN10541106
  • Text Lang
    ja
  • Data Source
    • CiNii Articles

Report a problem

Back to top