Object segmentation based on multi-resolution texture analysis

DOI IR (HANDLE)

Search this article

Description

This paper proposes the object segmentation method using multi-resolution texture analysis. The method consists of 1) pre-processing to produce multi-resolution images, 2) texture analysis using 1-Nearet Neighbor and Neural Networks, and 3) post-processing to combine the segmentation results. This structure is proposed in order to cope with the variety of the textures. The experiments using real test images prove that this multi-resolution approach could solve the cases with variety of the textures efficiently, and show that the method could achieve about 77% segmentation accuracy on average. The future study includes the application of the Liner Regression and an examination of some feature based approach.

Journal

Keywords

Details 詳細情報について

  • CRID
    1390853649760735872
  • NII Article ID
    120005400055
  • NII Book ID
    AA12222297
  • DOI
    10.15002/00009537
  • HANDLE
    10114/8760
  • ISSN
    18810667
  • Text Lang
    en
  • Article Type
    departmental bulletin paper
  • Data Source
    • JaLC
    • IRDB
    • CiNii Articles
  • Abstract License Flag
    Allowed

Report a problem

Back to top