ikmeans.c File Reference

Integer K-Means clustering - Definition. More...

#include "ikmeans.h"
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include "assert.h"
#include "ikmeans_init.tc"
#include "ikmeans_lloyd.tc"
#include "ikmeans_elkan.tc"

Functions
VlIKMFilt *	vl_ikm_new (int method)
	Create a new IKM quantizer.
void	vl_ikm_delete (VlIKMFilt *f)
	Delete IKM quantizer.
int	vl_ikm_train (VlIKMFilt *f, vl_uint8 const *data, int N)
	Train clusters.
void	vl_ikm_push (VlIKMFilt *f, vl_uint *asgn, vl_uint8 const *data, int N)
	Project data to clusters.
vl_uint	vl_ikm_push_one (vl_ikm_acc const *centers, vl_uint8 const *data, int M, int K)
	Project one datum to clusters.

---

Detailed Description

Author:

Brian Fulkerson

Andrea Vedaldi

---

Function Documentation

void vl_ikm_delete

(

VlIKMFilt *

f

)

Parameters:

f	IKM quantizer.

VlIKMFilt* vl_ikm_new

(

int

method

)

Parameters:

method

Clustering algorithm.

The function allocates initializes a new IKM quantizer to operate based algorithm method.

method has values in the enumerations VlIKMAlgorithms.

Returns:

new IKM quantizer.

void vl_ikm_push	(	VlIKMFilt *	f,
		vl_uint *	asgn,
		vl_uint8 const *	data,
		int	N
	)

Parameters:

f	IKM quantizer.
asgn	Assignments (out).
data	data.
N	number of data (N >= 1).

The function projects the data data on the integer K-means clusters specified by the IKM quantizer f. Notice that the quantizer must be initialized.

vl_uint vl_ikm_push_one	(	vl_ikm_acc const *	centers,
		vl_uint8 const *	data,
		int	M,
		int	K
	)

Parameters:

centers	centers.
data	datum to project.
K	number of centers.
M	dimensionality of the datum.

The function projects the specified datum data on the clusters specified by the centers centers.

Returns:

the cluster index.

int vl_ikm_train	(	VlIKMFilt *	f,
		vl_uint8 const *	data,
		int	N
	)

Parameters:

f	IKM quantizer.
data	data.
N	number of data (N >= 1).

Returns:

-1 if an overflow may have occurred.