An Optimized N-Dimensional Hough Filter for Detecting Spherical Image Objects
logo

Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/3129
An Insight Toolkit (ITK) algorithm for detection of spherical objects using Hough methods with voting is presented in this paper. Currently, the usage of Hough methods for detecting linear and circular elements exists for 2D images in ITK. The current work extends those filters in several ways. Firstly, the new filters operate on N-dimensional images. Secondly, they work in physical coordinates which is quite essential in medical imaging modalities. Thirdly, they are optimized (multi-threaded execution, stratified sampling etc.) for usage on large datasets and show a significant speedup even in 2D and on small images. Our implementation follows the same underlying mathematics of Hough transforms (as implemented by the 2D filters) but with some minor variations. The main variation lies in the pattern of voting that involves selecting voting regions easily and efficiently accessible to region iterators rather than cones that are difficult to generalize in higher dimensions. We include 2D example code, parameter settings and show the results generated on embryonic images of the zebrafish from optical microscopy.
Code
minus Automatic Testing Results by Insight-Journal Dashboard on Wed Sep 30 14:54:23 2009 for revision #1
starstarstarstarstar expertise: 5 sensitivity: 5
yellow This project passed all of its tests.
Click here for more details.

Go here to access the main testing dashboard.

Reviews
minus Fast and solid Multidimensional Hough Filter by Sergio Vera on 2010-12-23 11:54:24 for revision #1
starstarstarstarstar expertise: 2 sensitivity: 5
yellow
Summary:

The author presents a multidimensional Hough sphere detector, improving the originbal ITK filter that is limited to 2D.

Hypothesis:

Mathematically the algorithm is equivalent to the original one, but internal improvements provide fastest execution and detection of N-Dimensional spheres.

Evidence:

Example code in 3D and 2D detection is provided.

Open Science:

The work includes source and testing code to reproduce their work.

Reproducibility:

I was able to use the code withouth major problems.

Open source Contributions:

The code is highly usable, and the article includes enough information on the usage of the filter.

Free comment :

The code provides many improvements over the standard itk code:


1) Faster calculation time


2) works in N-Dimension images.


3) Works directy in physical coords which is nice in medical imaging.


With all the benefits, I recommend the inclussion of the filter inside the ITK toolkit.


Comment by Xpendexteshel Vigorda: yellow


Comment by Xpendexteshel Vigorda: yellow

Add a new review
Quick Comments


Resources
backyellow
Download All
Download Paper , View Paper
Download Source code
Github

Statistics more
backyellow
Global rating: starstarstarstarstar
Review rating: starstarstarstarstar [review]
Code rating: starstarstarstarstar
Paper Quality: plus minus

Information more
backyellow
Categories: Code speed optimization, Parallelization, SMP, Programming, Segmentation
Keywords: hough, segmentation, spherical objects
Toolkits: ITK, CMake
Export citation:

Share
backyellow
Share

Linked Publications more
backyellow
A Label Geometry Image Filter for Multiple Object Measurement A Label Geometry Image Filter for Multiple Object Measurement
by Padfield D., Miller J.
Diffeomorphic Demons Using ITK's Finite Difference Solver Hierarchy Diffeomorphic Demons Using ITK's Finite Difference Solver Hierarchy
by Vercauteren T., Pennec X., Perchant A., Ayache N.

View license
Loading license...

Send a message to the author
main_flat
Powered by Midas