OpenCV  3.4.20-dev
Open Source Computer Vision
Enumerations | Functions

Enumerations

enum  cv::KmeansFlags {
  cv::KMEANS_RANDOM_CENTERS = 0,
  cv::KMEANS_PP_CENTERS = 2,
  cv::KMEANS_USE_INITIAL_LABELS = 1
}
 k-Means flags More...
 

Functions

double cv::kmeans (InputArray data, int K, InputOutputArray bestLabels, TermCriteria criteria, int attempts, int flags, OutputArray centers=noArray())
 Finds centers of clusters and groups input samples around the clusters. More...
 
template<typename _Tp , class _EqPredicate >
int partition (const std::vector< _Tp > &_vec, std::vector< int > &labels, _EqPredicate predicate=_EqPredicate())
 Splits an element set into equivalency classes. More...
 

Detailed Description

Enumeration Type Documentation

◆ KmeansFlags

#include <opencv2/core.hpp>

k-Means flags

Enumerator
KMEANS_RANDOM_CENTERS 
Python: cv.KMEANS_RANDOM_CENTERS

Select random initial centers in each attempt.

KMEANS_PP_CENTERS 
Python: cv.KMEANS_PP_CENTERS

Use kmeans++ center initialization by Arthur and Vassilvitskii [Arthur2007].

KMEANS_USE_INITIAL_LABELS 
Python: cv.KMEANS_USE_INITIAL_LABELS

During the first (and possibly the only) attempt, use the user-supplied labels instead of computing them from the initial centers. For the second and further attempts, use the random or semi-random centers. Use one of KMEANS_*_CENTERS flag to specify the exact method.

Function Documentation

◆ kmeans()

double cv::kmeans ( InputArray  data,
int  K,
InputOutputArray  bestLabels,
TermCriteria  criteria,
int  attempts,
int  flags,
OutputArray  centers = noArray() 
)
Python:
cv.kmeans(data, K, bestLabels, criteria, attempts, flags[, centers]) -> retval, bestLabels, centers

#include <opencv2/core.hpp>

Finds centers of clusters and groups input samples around the clusters.

The function kmeans implements a k-means algorithm that finds the centers of cluster_count clusters and groups the input samples around the clusters. As an output, \(\texttt{bestLabels}_i\) contains a 0-based cluster index for the sample stored in the \(i^{th}\) row of the samples matrix.

Note
  • (Python) An example on K-means clustering can be found at opencv_source_code/samples/python/kmeans.py
Parameters
dataData for clustering. An array of N-Dimensional points with float coordinates is needed. Examples of this array can be:
  • Mat points(count, 2, CV_32F);
  • Mat points(count, 1, CV_32FC2);
  • Mat points(1, count, CV_32FC2);
  • std::vector<cv::Point2f> points(sampleCount);
KNumber of clusters to split the set by.
bestLabelsInput/output integer array that stores the cluster indices for every sample.
criteriaThe algorithm termination criteria, that is, the maximum number of iterations and/or the desired accuracy. The accuracy is specified as criteria.epsilon. As soon as each of the cluster centers moves by less than criteria.epsilon on some iteration, the algorithm stops.
attemptsFlag to specify the number of times the algorithm is executed using different initial labellings. The algorithm returns the labels that yield the best compactness (see the last function parameter).
flagsFlag that can take values of cv::KmeansFlags
centersOutput matrix of the cluster centers, one row per each cluster center.
Returns
The function returns the compactness measure that is computed as

\[\sum _i \| \texttt{samples} _i - \texttt{centers} _{ \texttt{labels} _i} \| ^2\]

after every attempt. The best (minimum) value is chosen and the corresponding labels and the compactness value are returned by the function. Basically, you can use only the core of the function, set the number of attempts to 1, initialize labels each time using a custom algorithm, pass them with the ( flags = KMEANS_USE_INITIAL_LABELS ) flag, and then choose the best (most-compact) clustering.
Examples:
samples/cpp/kmeans.cpp.

◆ partition()

template<typename _Tp , class _EqPredicate >
int partition ( const std::vector< _Tp > &  _vec,
std::vector< int > &  labels,
_EqPredicate  predicate = _EqPredicate() 
)

#include <opencv2/core/operations.hpp>

Splits an element set into equivalency classes.

The generic function partition implements an \(O(N^2)\) algorithm for splitting a set of \(N\) elements into one or more equivalency classes, as described in http://en.wikipedia.org/wiki/Disjoint-set_data_structure . The function returns the number of equivalency classes.

Parameters
_vecSet of elements stored as a vector.
labelsOutput vector of labels. It contains as many elements as vec. Each label labels[i] is a 0-based cluster index of vec[i].
predicateEquivalence predicate (pointer to a boolean function of two arguments or an instance of the class that has the method bool operator()(const _Tp& a, const _Tp& b) ). The predicate returns true when the elements are certainly in the same class, and returns false if they may or may not be in the same class.