[Insight-users] Contribution for itk

[antiga at marionegri.it]

Hi Luis,
 if you like them and find them useful, I have these classes around I'd 
like to contribute to itk 

1. itk::Statistics::OtsuThresholdsCalculator: class in the Statistics
namespace which computes N thresholds by maximizing the between-class
variance of the classes. Input: itkHistogram. Output: vector of
thresholds.
 In fact there's already an OtsuThresholdImageCalculator, but it's a bit
odd: it's derived from itk::Object, it takes in input an itk::Image
(therefore you can't work with subsamples) and it's limited to 1
threshold.

2. itk::Statistics::HistogramAlgorithmBase: base class for the above 
class, which behaves like SampleAlgorithmBase.

3. itk::ThresholdLabelerImageFilter: derived from UnaryFunctorImageFilter. 
It takes a vector of sorted thresholds in input (e.g., the output of 
OtsuThresholdImageCalculator) and produces a labeled image in output. One 
can specify the label offset.

Let me know and I'll mail them to you

Ciao

Luca

-- 
Luca Antiga, PhD
----------------------------------------------
Biomedical Technologies Laboratory
Bioengineering Department, 
Mario Negri Institute
Villa Camozzi, 24020, Ranica (BG), Italy
----------------------------------------------
phone: +39 035 4535-381
email: antiga at marionegri.it
web:   http://villacamozzi.marionegri.it/~luca
----------------------------------------------