File Exchange

image thumbnail

Segmentation using morphology

version 1.1.0.0 (67.4 KB) by Benjamin I
Segmentation of locally darker somewhat circular regions using a morphology based method

18 Downloads

Updated 21 Mar 2016

View License on GitHub

This simple method can be used to segment locally darker regions in a grayscale image that have a somewhat circular appearance.
demo.m performs a segmentation on the example image recon_test.png.

The method has been used in medical imaging as part of an airway segmentation method to extract the 3D airways. See http://www.lungworkshop.org/2009/proc2009/297.pdf for details of the full method and http://image.diku.dk/exact/exact_team_result.php?team_id=15 for results.

Comments and Ratings (5)

Lena

Lena (view profile)

wang wang

Benjamin I

@ debasmita bhoumik,

The easiest option would be to invert your image before performing the segmentation.

Something like:
Inew = max(I(:)) - I

This method is for " segment locally darker regions in a grayscale image that have a somewhat circular appearance. "

I want to segment locally lighter region.. what should i do (i am a very beginner student in matlab)

please I want matalab program to cut ROI from dicom image

Updates

1.1.0.0

link to github

MATLAB Release Compatibility
Created with R2012b
Compatible with any release
Platform Compatibility
Windows macOS Linux

Discover Live Editor

Create scripts with code, output, and formatted text in a single executable document.


Learn About Live Editor