bagofwords.cpp 6 KB
Newer Older
wester committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43
/*M///////////////////////////////////////////////////////////////////////////////////////
//
//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
//  By downloading, copying, installing or using the software you agree to this license.
//  If you do not agree to this license, do not download, install,
//  copy or use the software.
//
//
//                        Intel License Agreement
//                For Open Source Computer Vision Library
//
// Copyright (C) 2000, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
//   * Redistribution's of source code must retain the above copyright notice,
//     this list of conditions and the following disclaimer.
//
//   * Redistribution's in binary form must reproduce the above copyright notice,
//     this list of conditions and the following disclaimer in the documentation
//     and/or other materials provided with the distribution.
//
//   * The name of Intel Corporation may not be used to endorse or promote products
//     derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/

#include "precomp.hpp"

wester committed
44 45
using namespace std;

wester committed
46 47 48
namespace cv
{

wester committed
49
BOWTrainer::BOWTrainer()
wester committed
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71
{}

BOWTrainer::~BOWTrainer()
{}

void BOWTrainer::add( const Mat& _descriptors )
{
    CV_Assert( !_descriptors.empty() );
    if( !descriptors.empty() )
    {
        CV_Assert( descriptors[0].cols == _descriptors.cols );
        CV_Assert( descriptors[0].type() == _descriptors.type() );
        size += _descriptors.rows;
    }
    else
    {
        size = _descriptors.rows;
    }

    descriptors.push_back(_descriptors);
}

wester committed
72
const vector<Mat>& BOWTrainer::getDescriptors() const
wester committed
73 74 75 76
{
    return descriptors;
}

wester committed
77
int BOWTrainer::descripotorsCount() const
wester committed
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
{
    return descriptors.empty() ? 0 : size;
}

void BOWTrainer::clear()
{
    descriptors.clear();
}

BOWKMeansTrainer::BOWKMeansTrainer( int _clusterCount, const TermCriteria& _termcrit,
                                    int _attempts, int _flags ) :
    clusterCount(_clusterCount), termcrit(_termcrit), attempts(_attempts), flags(_flags)
{}

Mat BOWKMeansTrainer::cluster() const
{
    CV_Assert( !descriptors.empty() );

a  
Kai Westerkamp committed
96 97 98 99 100
    int descCount = 0;
    for( size_t i = 0; i < descriptors.size(); i++ )
        descCount += descriptors[i].rows;

    Mat mergedDescriptors( descCount, descriptors[0].cols, descriptors[0].type() );
wester committed
101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132
    for( size_t i = 0, start = 0; i < descriptors.size(); i++ )
    {
        Mat submut = mergedDescriptors.rowRange((int)start, (int)(start + descriptors[i].rows));
        descriptors[i].copyTo(submut);
        start += descriptors[i].rows;
    }
    return cluster( mergedDescriptors );
}

BOWKMeansTrainer::~BOWKMeansTrainer()
{}

Mat BOWKMeansTrainer::cluster( const Mat& _descriptors ) const
{
    Mat labels, vocabulary;
    kmeans( _descriptors, clusterCount, labels, termcrit, attempts, flags, vocabulary );
    return vocabulary;
}


BOWImgDescriptorExtractor::BOWImgDescriptorExtractor( const Ptr<DescriptorExtractor>& _dextractor,
                                                      const Ptr<DescriptorMatcher>& _dmatcher ) :
    dextractor(_dextractor), dmatcher(_dmatcher)
{}

BOWImgDescriptorExtractor::~BOWImgDescriptorExtractor()
{}

void BOWImgDescriptorExtractor::setVocabulary( const Mat& _vocabulary )
{
    dmatcher->clear();
    vocabulary = _vocabulary;
wester committed
133
    dmatcher->add( vector<Mat>(1, vocabulary) );
wester committed
134 135 136 137 138 139 140
}

const Mat& BOWImgDescriptorExtractor::getVocabulary() const
{
    return vocabulary;
}

wester committed
141 142
void BOWImgDescriptorExtractor::compute( const Mat& image, vector<KeyPoint>& keypoints, Mat& imgDescriptor,
                                         vector<vector<int> >* pointIdxsOfClusters, Mat* _descriptors )
wester committed
143 144 145 146 147 148 149 150
{
    imgDescriptor.release();

    if( keypoints.empty() )
        return;

    int clusterCount = descriptorSize(); // = vocabulary.rows

wester committed
151 152 153 154
    // Compute descriptors for the image.
    Mat descriptors;
    dextractor->compute( image, keypoints, descriptors );

wester committed
155
    // Match keypoint descriptors to cluster center (to vocabulary)
wester committed
156 157
    vector<DMatch> matches;
    dmatcher->match( descriptors, matches );
wester committed
158 159 160 161 162 163 164 165

    // Compute image descriptor
    if( pointIdxsOfClusters )
    {
        pointIdxsOfClusters->clear();
        pointIdxsOfClusters->resize(clusterCount);
    }

wester committed
166 167
    imgDescriptor = Mat( 1, clusterCount, descriptorType(), Scalar::all(0.0) );
    float *dptr = (float*)imgDescriptor.data;
wester committed
168 169 170 171 172 173 174 175 176 177 178 179
    for( size_t i = 0; i < matches.size(); i++ )
    {
        int queryIdx = matches[i].queryIdx;
        int trainIdx = matches[i].trainIdx; // cluster index
        CV_Assert( queryIdx == (int)i );

        dptr[trainIdx] = dptr[trainIdx] + 1.f;
        if( pointIdxsOfClusters )
            (*pointIdxsOfClusters)[trainIdx].push_back( queryIdx );
    }

    // Normalize image descriptor.
wester committed
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195
    imgDescriptor /= descriptors.rows;

    // Add the descriptors of image keypoints
    if (_descriptors) {
        *_descriptors = descriptors.clone();
    }
}

int BOWImgDescriptorExtractor::descriptorSize() const
{
    return vocabulary.empty() ? 0 : vocabulary.rows;
}

int BOWImgDescriptorExtractor::descriptorType() const
{
    return CV_32FC1;
wester committed
196 197 198
}

}