songsenand
/
cgal
mirror of https://github.com/CGAL/cgal
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update doc of PCA: the kernel is the last argument in the code.

This commit is contained in:
Pierre Alliez 2010-09-03 15:38:26 +00:00
parent 57666e687c
commit 4f47f8e307
2 changed files with 10 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
Principal_component_analysis/doc_tex/Principal_component_analysis_ref/linear_least_squares_fitting_2.tex
View File

@ -26,15 +26,14 @@ The best fitting line minimizes the sum of squared distances from all points com
InputIterator beyond,
typename K::Line_2 & line,
typename K::Point_2 & centroid,
const K & k,
const Tag& tag);}
const Tag & tag,
const K & k);}
{ computes the best fitting 2D line of a 2D object set in the range [\ccc{first},\ccc{beyond}). The value returned is a fitting quality between $0$ and $1$, where $0$ means that the variance is the same along any line (a horizontal line going through the centroid is output by default), and $1$ means that the variance is null orthogonally to the best fitting line (hence the fit is perfect).
\ccPrecond{first != beyond.} }
The class \ccc{K} is the kernel in which the type \ccc{InputIterator::value_type} is defined. It can be omitted and deduced automatically from the value type.\\
The tag \ccc{tag} identifies the dimension to be considered from the objects. For point sets it should be 0. For segments it can be 1 or 0 according to whether one wants to fit the whole segment or just their end points. For triangles it can range from 0 to 2 according to whether one wants to fit either the triangle points, the segments or the whole triangles. For rectangles it can range from 0 to 2 according to whether one wants to fit either the corner points, the segments, or the whole rectangles. For circles it can be 1 or 2 according to whether one wants to fit either the circles or the whole discs. For triangles it ranges from 0 to 2 according to whether one wants to fit either the points, the segments or the whole triangles.
The class \ccc{K} is the kernel in which the type \ccc{InputIterator::value_type} is defined. It can be omitted and deduced automatically from the value type.\\
\ccHeading{Requirements}
@ -45,7 +44,7 @@ The tag \ccc{tag} identifies the dimension to be considered from the objects. Fo
\item \ccc{line} is the best fitting line computed.
\item \ccc{centroid} is the centroid computed. This parameter is optional and can be
omitted.
\item \ccc{t} is the tag identifying the dimension to be considered from the objects. It should be one of \ccc{Dimension_tag<0>}, \ccc{Dimension_tag<1>} or \ccc{Dimension_tag<2>}. Also, it should not be of dimension greater than the geometry of the object. For example, a \ccc{Segment} can not have a \ccc{Dimension_tag<2>} tag.
\item \ccc{tag} is the tag identifying the dimension to be considered from the objects. It should be one of \ccc{Dimension_tag<0>}, \ccc{Dimension_tag<1>} or \ccc{Dimension_tag<2>}. Also, it should not be of dimension greater than the geometry of the object. For example, a \ccc{Segment} can not have a \ccc{Dimension_tag<2>} tag.
\end{enumerate}
\end{ccRefFunction}

12
Principal_component_analysis/doc_tex/Principal_component_analysis_ref/linear_least_squares_fitting_3.tex
View File

@ -27,17 +27,17 @@ The fitting quality property is characterized by the values of the three eigenva
InputIterator beyond,
typename K::Line_3& line,
typename K::Point_3& centroid,
const K& k,
const Tag& tag);}
const Tag& tag,
const K& k);}
{ computes the best fitting 3D line of a 3D object set in the range
[\ccc{first},\ccc{beyond}). The value returned is a fitting quality
between $0$ and $1$, where $0$ means that the variance is the same
along any line contained within the best fitting plane, and $1$ means that the variance is null orthogonally to the best fitting line (hence the fit is perfect). }
The class \ccc{K} is the kernel in which the type \ccc{InputIterator::value_type} is defined. It can be omitted and deduced automatically from the value type.
The tag \ccc{tag} identifies the dimension to be considered from the objects. For point sets it should be 0. For segment sets it could be 1 or 0 according to whether one wants to fit the entire segments or just the end points. For triangle sets it can range from 0 to 2 according to whether one wants to fit either the corner points, the segments or the whole triangles. For cuboid sets it can range from 0 to 3 according to whether one wants to fit either the corners, the segments, the faces or the whole solid cuboids. For sphere sets it can be 2 or 3 according to whether one wants to fit either the surface of the spheres or the whole solid balls. For tetrahedron sets it can range from 0 to 3 according to whether one wants to fit either the points, the segments, the surface triangles or the whole solid tetrahedra.
The class \ccc{K} is the kernel in which the type \ccc{InputIterator::value_type} is defined. It can be omitted and deduced automatically from the value type.
\ccHeading{Requirements}
\begin{enumerate}
@ -56,8 +56,8 @@ The tag \ccc{tag} identifies the dimension to be considered from the objects. Fo
InputIterator beyond,
typename K::Plane_3& plane,
typename K::Point_3& centroid,
const K& k,
const Tag& tag);}
const Tag& tag,
const K& k);}
{ computes the best fitting 3D plane of a 3D object set in the range
[\ccc{first},\ccc{beyond}). The value returned is a fitting quality
between $0$ and $1$, where $0$ means that the variance is the same