From d85fb29b8e891588aea3b64101f5bbc7feca29d6 Mon Sep 17 00:00:00 2001
From: Julien Michel <julien.michel@orfeo-toolbox.org>
Date: Fri, 27 Jan 2012 14:50:28 +0100
Subject: [PATCH] DOC: Enhancing documentation of the Dimension Reduction
chapter
---
Examples/DimensionReduction/ICAExample.cxx | 18 ++++++++++------
Examples/DimensionReduction/MNFExample.cxx | 21 ++++++++++++++-----
.../MaximumAutocorrelationFactor.cxx | 11 +++++++++-
Examples/DimensionReduction/NAPCAExample.cxx | 8 +++----
4 files changed, 42 insertions(+), 16 deletions(-)
diff --git a/Examples/DimensionReduction/ICAExample.cxx b/Examples/DimensionReduction/ICAExample.cxx
index 7277842d80..5078a9793f 100644
--- a/Examples/DimensionReduction/ICAExample.cxx
+++ b/Examples/DimensionReduction/ICAExample.cxx
@@ -31,10 +31,15 @@
//
// This example illustrates the use of the
// \doxygen{otb}{FastICAImageFilter}.
-// This filter computes a Principal Component Analysis using an
-// efficient method based on the inner product in order to compute the
-// covariance matrix.
+// This filter computes a Fast Independant Components Analysis transform.
//
+// Like Principal Components Analysis, FastICA computes a set of
+// orthogonal linear combinations, but the criterion of Fast ICA is
+// different: instead of maximizing variance, it tries to maximize
+// stastistical independance between components. In Fast ICA,
+// statistical independance is mesured by evaluating non-Gaussianity
+// of the components, and the maximization is done in an iterative way.
+
// The first step required to use this filter is to include its header file.
//
// Software Guide : EndLatex
@@ -144,7 +149,7 @@ int main(int argc, char* argv[])
// Software Guide : EndCodeSnippet
// Software Guide : BeginLatex
//
- // We finally plug the pipeline and trigger the PCA computation with
+ // We finally plug the pipeline and trigger the ICA computation with
// the method \code{Update()} of the writer.
//
// Software Guide : EndLatex
@@ -159,7 +164,7 @@ int main(int argc, char* argv[])
// Software Guide : BeginLatex
//
// \doxygen{otb}{FastICAImageFilter} allows also to compute inverse
- // transformation from PCA coefficients. In reverse mode, the
+ // transformation from ICA coefficients. In reverse mode, the
// covariance matrix or the transformation matrix
// (which may not be square) has to be given.
//
@@ -173,7 +178,8 @@ int main(int argc, char* argv[])
invFilter->SetMeanValues( FastICAfilter->GetMeanValues() );
invFilter->SetStdDevValues( FastICAfilter->GetStdDevValues() );
invFilter->SetTransformationMatrix( FastICAfilter->GetTransformationMatrix() );
- invFilter->SetPCATransformationMatrix( FastICAfilter->GetPCATransformationMatrix() );
+ invFilter->SetPCATransformationMatrix(
+ FastICAfilter->GetPCATransformationMatrix() );
invFilter->SetInput(FastICAfilter->GetOutput());
WriterType::Pointer invWriter = WriterType::New();
diff --git a/Examples/DimensionReduction/MNFExample.cxx b/Examples/DimensionReduction/MNFExample.cxx
index 8977d85bdb..bc4d6df850 100644
--- a/Examples/DimensionReduction/MNFExample.cxx
+++ b/Examples/DimensionReduction/MNFExample.cxx
@@ -30,11 +30,22 @@
// Software Guide : BeginLatex
//
// This example illustrates the use of the
-// \doxygen{otb}{MNFImageFilter}.
-// This filter computes a Principal Component Analysis using an
+// \doxygen{otb}{MNFImageFilter}. This filter computes a Minimum
+// Noise Fraction transform \cite{nielsen2011kernel} using an
// efficient method based on the inner product in order to compute the
// covariance matrix.
//
+// The Minimum Noise Fraction transform is a sequence of two Principal
+// Components Analysis transform. The first transform is based on an
+// estimated covariance matrix of the noise, and intends to whiten the
+// input image (noise with unit variance and no correlation between
+// bands).
+//
+// The second Principal Components Analysis is then applied to the
+// noise-whitened image, giving the Minimum Noise Fraction transform.
+//
+// In this implementation, noise is estimated from a local window.
+//
// The first step required to use this filter is to include its header file.
//
// Software Guide : EndLatex
@@ -100,7 +111,7 @@ int main(int argc, char* argv[])
// Software Guide : EndLatex
// SoftwareGuide : BeginCodeSnippet
- typedef otb::LocalActivityVectorImageFilter< ImageType, ImageType > NoiseFilterType;
+ typedef otb::LocalActivityVectorImageFilter<ImageType,ImageType> NoiseFilterType;
// SoftwareGuide : EndCodeSnippet
@@ -167,7 +178,7 @@ int main(int argc, char* argv[])
// Software Guide : EndCodeSnippet
// Software Guide : BeginLatex
//
- // We finally plug the pipeline and trigger the PCA computation with
+ // We finally plug the pipeline and trigger the MNF computation with
// the method \code{Update()} of the writer.
//
// Software Guide : EndLatex
@@ -182,7 +193,7 @@ int main(int argc, char* argv[])
// Software Guide : BeginLatex
//
// \doxygen{otb}{MNFImageFilter} allows also to compute inverse
- // transformation from PCA coefficients. In reverse mode, the
+ // transformation from MNF coefficients. In reverse mode, the
// covariance matrix or the transformation matrix
// (which may not be square) has to be given.
//
diff --git a/Examples/DimensionReduction/MaximumAutocorrelationFactor.cxx b/Examples/DimensionReduction/MaximumAutocorrelationFactor.cxx
index ffd26e2538..6dd258860a 100644
--- a/Examples/DimensionReduction/MaximumAutocorrelationFactor.cxx
+++ b/Examples/DimensionReduction/MaximumAutocorrelationFactor.cxx
@@ -28,7 +28,16 @@
// Software Guide : BeginLatex
// This example illustrates the class
-// \doxygen{otb}{MaximumAutocorrelationFactorImageFilter} ...
+// \doxygen{otb}{MaximumAutocorrelationFactorImageFilter}, which
+// performs a Maximum Autocorrelation Factor transform \cite{nielsen2011kernel}. Like
+// PCA, MAF tries to find a set of orthogonal linear transform, but
+// the criterion to maximize is the auto-correlation rather than the
+// variance.
+//
+// Auto-correlation is the correlation between the component and a
+// unitary shifted version of the component.
+//
+// Please note that the inverse transform is not implemented yet.
//
// We start by including the corresponding header file.
//
diff --git a/Examples/DimensionReduction/NAPCAExample.cxx b/Examples/DimensionReduction/NAPCAExample.cxx
index cf24000d18..6ecc58b916 100644
--- a/Examples/DimensionReduction/NAPCAExample.cxx
+++ b/Examples/DimensionReduction/NAPCAExample.cxx
@@ -100,7 +100,7 @@ int main(int argc, char* argv[])
// Software Guide : EndLatex
// SoftwareGuide : BeginCodeSnippet
- typedef otb::LocalActivityVectorImageFilter< ImageType, ImageType > NoiseFilterType;
+ typedef otb::LocalActivityVectorImageFilter<ImageType,ImageType> NoiseFilterType;
// SoftwareGuide : EndCodeSnippet
@@ -167,7 +167,7 @@ int main(int argc, char* argv[])
// Software Guide : EndCodeSnippet
// Software Guide : BeginLatex
//
- // We finally plug the pipeline and trigger the PCA computation with
+ // We finally plug the pipeline and trigger the NA-PCA computation with
// the method \code{Update()} of the writer.
//
// Software Guide : EndLatex
@@ -182,7 +182,7 @@ int main(int argc, char* argv[])
// Software Guide : BeginLatex
//
// \doxygen{otb}{NAPCAImageFilter} allows also to compute inverse
- // transformation from PCA coefficients. In reverse mode, the
+ // transformation from NA-PCA coefficients. In reverse mode, the
// covariance matrix or the transformation matrix
// (which may not be square) has to be given.
//
@@ -209,7 +209,7 @@ int main(int argc, char* argv[])
// Software Guide : BeginLatex
// Figure~\ref{fig:NAPCA_FILTER} shows the result of applying forward
- // and reverse NAPCA transformation to a 8 bands Wordlview2 image.
+ // and reverse NA-PCA transformation to a 8 bands Wordlview2 image.
// \begin{figure}
// \center
// \includegraphics[width=0.32\textwidth]{napca-input-pretty.eps}
--
GitLab