Abstract
The itkLabelGeometryImageFilter is a new ITK filter that enables the measurement of geometric features of labeled objects. It calculates features similar to the "regionprops" command of Matlab. It is related to the itkLabelStatisticsImageFilter in that both filters measure features of labeled masks. It differs, however, in that it measures geometric features of the objects themselves rather than statistics of image intensities under the masks defined by the objects. This document describes the mathematical background of the geometric features measured by this filter and describes the framework of the code, which is structured to enable easy expandability as new object features are desired.
Keywords
Source Code and Data
Reviews
Xiaoxiao Liu
Tuesday 26 August 2008
I had some experience with processing labeled images using this filter.
It is a very neat filter that wraps many useful statistics features from labeled regions or objects. It uses hash map to store and look up the features for each labeled region, which makes the filter computationally efficient.
The code itself is very well documented and structured.
Kwame Kutten
Sunday 24 August 2008
Summary:
The authors described a filter which can be used to determine the properties (volumes, centroids, ...) of regions in an labeled ND image. It is similar to MATLAB’s "regionprops" command.
Open Science:
The authors provided the source code and a test image. This was enough to replicate their work.
Reproducibility:
I was able to reproduce the authors’ work. The test code compiled and ran without any modifications in Visual Studio 2005 on Windows XP. I integrated the code into a project I am working on. I used this filter to find the centroids, volumes and eccentricities of regions in a 2D binary image.
Use of Open Source Software:
The authors used ITK, an open source library.
Open Source Contributions:
The authors provided the filter’s source code, test code and a test image.
Code Quality:
The test code (itkLabelGeometryImageFilterTest.cxx) and source was easy to follow and understand.
Additional Comments:
This was very useful in translating MATLAB code which used "regionprops" to C++.
Zhaohui Sun
Tuesday 19 August 2008
I have used the filter in my project. It has some nice features that I wanted but could not find in ITK. The filter has worked well and I have not had any errors so far.