Proposals:Refactoring Statistics Framework 2007 Miscellaneous: Difference between revisions

From KitwarePublic
Jump to navigationJump to search
No edit summary
 
Line 7: Line 7:
== CovarianceCalculator ==
== CovarianceCalculator ==
* Known Mean versus estimated mean (incorrect equation: N versus N-1)
* Known Mean versus estimated mean (incorrect equation: N versus N-1)
== DistanceMetric ==
== Distance Metric ==
* Room to expand to other metrics (1_1, 1_inf, Mahalanobis
* Room to expand to other metrics (1_1, 1_inf, Mahalanobis)
 
== Distance To Centroid Membership Function ==
 
* Why is 1_2 distance hard coded ? as opposed to using a distance metric ?
* Title centroid is unnecessarily narrow
* Why not a generic Distance Membership Function where metrics are plugged in ?
 
== Distances ==
 
* itkEuclideanDistance
* itkMahalanobisDistanceMembershipFunction
 
== ImageToCoocurrenceListAdaptor ==
 
* This is not really an adaptor, it generates new data.
* Should it be called Generator ? or Filter ?
 
== ListSampleBase ==
 
* Very lightweight, probably unnecessary
* Only provides a Search() method, and this method probably shouldn't be there
 
== NeighborhoodSampler ==
 
* Sample with spherical (1_2_ neighborhood)
* Allow other metrics ?
 
== SampleAlgorithmBase ==
 
* Very lightweight, no obvious benefit
* Is it a candidate for deprecation ?

Revision as of 12:24, 3 April 2007

Miscellaneous Issues

Most of these issues were identified by Brad Davis.

CovarianceCalculator

  • Known Mean versus estimated mean (incorrect equation: N versus N-1)

Distance Metric

  • Room to expand to other metrics (1_1, 1_inf, Mahalanobis)

Distance To Centroid Membership Function

  • Why is 1_2 distance hard coded ? as opposed to using a distance metric ?
  • Title centroid is unnecessarily narrow
  • Why not a generic Distance Membership Function where metrics are plugged in ?

Distances

  • itkEuclideanDistance
  • itkMahalanobisDistanceMembershipFunction

ImageToCoocurrenceListAdaptor

  • This is not really an adaptor, it generates new data.
  • Should it be called Generator ? or Filter ?

ListSampleBase

  • Very lightweight, probably unnecessary
  • Only provides a Search() method, and this method probably shouldn't be there

NeighborhoodSampler

  • Sample with spherical (1_2_ neighborhood)
  • Allow other metrics ?

SampleAlgorithmBase

  • Very lightweight, no obvious benefit
  • Is it a candidate for deprecation ?