Multiscale segmentation of remotely sensed images using Pairwise Markov Chains


Papila I., Ersoy O.

IEEE Antennas-and-Propagation-Society International Symposium, Monterrey, Mexico, 20 - 26 June 2004, pp.2123-2126 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/aps.2004.1330629
  • City: Monterrey
  • Country: Mexico
  • Page Numbers: pp.2123-2126

Abstract

Among the statistical approaches to image modeling, recently, Markov Random Fields have gained significant attention especially in texture segmentation. Different from Markov Random Fields, in Pairwise Markov Chains the class field is not neccassarily Markov Field, an advantage to leads in segmentation of texture images without any model approximation. In this study supervised texture segmentation of multiscale image is introduced in pairwise Markov Chain tree model using wavelet-domain. The essence of this tree-structured probabilistic graph is based on capturing the statistical properties of the wavelet transforms and the intrinsic characters of textural regions of any multispectral image.