Regional segmentaion of multispectral image using local texture/spectral joint histgram

We present a new method for segmentation of multispectral image. The method can be divided into three steps. Firstly, the image is partitioned into small regions using mean shift algorithm; then texture-spectral joint histograms are extracted from those regions; thirdly, an adaptive, multiscale merg...

Full description

Saved in:
Bibliographic Details
Main Authors: Leiguang Wang, Chen Zheng, Qinling Dai
Format: Conference Proceeding
Language:English
Subjects:
Corporate acquisitions
Educational institutions
Filtering
Forestry
Image segmentation
Joint histrgam
Joints
Markov processes
mean shift segmentation
segmentation
spectral
texture
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a new method for segmentation of multispectral image. The method can be divided into three steps. Firstly, the image is partitioned into small regions using mean shift algorithm; then texture-spectral joint histograms are extracted from those regions; thirdly, an adaptive, multiscale merging process is defined to get final result. Experiments on several synthetic images show that the method is superior to two competitors.
DOI:10.1109/RSETE.2011.5964783