explanation on new cvspilltree in opencv subversion

checkout the new opencv.

in real world data, in lower dimension, spill tree outperform bbf by an order of computing time.

spill tree approximation result in 4 ms

best-bin-first approximation result in 20 ms

naive search result in 61 ms

test data can be found in: http://kdd.ics.uci.edu/databases/CorelFeatures/CorelFeatures.html
the test was done with LayoutHistogram.asc file.

#include "cv.h"
#include <iostream>
int main()
{
int n = 66615;//68039;
int d = 32;
int k = 10;
CvRNG rng_state = cvRNG(0xffffffff);
CvMat* toy = cvCreateMat( n, d, CV_64FC1 );
CvMat* vector = cvCreateMat( 1, d, CV_64FC1 );
//cvRandArr( &rng_state, toy, CV_RAND_UNI, cvRealScalar(0), cvRealScalar(1) );
//cvRandArr( &rng_state, vector, CV_RAND_UNI, cvRealScalar(0), cvRealScalar(1) );
freopen( "LayoutHistogram.asc", "r", stdin );
double* toyv = toy->data.db;
int rn = cvRandInt( &rng_state ) % (n+1);
double tmp;
for ( int i = 0; i <= n; i++ )
{
int id;
std::cin>>id;
if ( rn == i )
{
double* vev = vector->data.db;
for ( int j = 0; j < d; j++ )
{
std::cin>>tmp;
*vev = tmp;
vev++;
}
} else {
for ( int j = 0; j < d; j++ )
{
std::cin>>tmp;
*toyv = tmp;
toyv++;
}
}
}
printf( "data generated/n" );
long long t;
t = cvGetTickCount();
CvFeatureTree* tr = cvCreateSpillTree( toy, 2, .7, .1 );
t = cvGetTickCount() - t;
printf( "spill tree created in %lld ms./n", t/1000000 );
double* vv = vector->data.db;
printf( "test drive: " );
for ( int i = 0; i < d-1; i++ )
printf( "%f ", vv[i] );
printf( "%f/n", vv[d-1] );
CvMat* res = cvCreateMat( 1, k, CV_32SC1 );
CvMat* dist = cvCreateMat( 1, k, CV_64FC1 );
t = cvGetTickCount();
cvFindFeatures( tr, vector, res, dist, k, 0 );
t = cvGetTickCount() - t;
printf( "spill tree approximation result in %lld ms:/n", t/1000000 );
vv = dist->data.db;
int* idx = res->data.i;
for ( int i = 0; i < k; i++ )
printf( "---sim: %f---i: %d---/n", vv[i], idx[i] );
cvReleaseFeatureTree( tr );
t = cvGetTickCount();
CvFeatureTree* bbf = cvCreateKDTree( toy );
t = cvGetTickCount() - t;
printf( "kd tree created in %lld ms./n", t/1000000 );
t = cvGetTickCount();
cvFindFeatures( bbf, vector, res, dist, k, 20 );
t = cvGetTickCount() - t;
printf( "best-bin-first approximation result in %lld ms:/n", t/1000000 );
vv = dist->data.db;
idx = res->data.i;
for ( int i = 0; i < k; i++ )
printf( "---sim: %f---i: %d---/n", vv[i], idx[i] );
CvMat** data = (CvMat**)cvAlloc( sizeof(CvMat*)*n );
for ( int i = 0; i < n; i++ )
{
data[i] = cvCreateMatHeader( 1, d, CV_64FC1 );
cvSetData( data[i], toy->data.db+i*d, toy->step );
}
double* norms = (double*)cvAlloc( sizeof(double)*n );
t = cvGetTickCount();
for ( int i = 0; i < n; i++ )
norms[i] = cvNorm( data[i], vector );
for ( int i = 0; i < k; i++ )
{
int l = i;
for ( int j = i+1; j < n; j++ )
if ( norms[j] < norms[l] )
l = j;
double c;
CV_SWAP( norms[l], norms[i], c );
}
t = cvGetTickCount() - t;
printf( "naive search result in %lld ms/n", t/1000000 );
for ( int i = 0; i < k; i++ )
printf( "---sim: %f---/n", norms[i] );
return 0;
}