示例#1
0
variant _1_kMeans(std::vector<std::vector<double>> img, std::vector<std::vector<double>> old_centers_v, int K, double epsilon kMeans_DOWN__1_kMeans_decl) {
    cv::Mat centers(cv::Scalar(0)), old_centers(old_centers_v);
    cv::Mat data0(img);
    bool isrow = data0.rows == 1 && data0.channels() > 1;
    int N = !isrow ? data0.rows : data0.cols;
    int dims = (!isrow ? data0.cols : 1) * data0.channels();
    int type = data0.depth();

    if (!(data0.dims <= 2 && type == CV_32F && K > 0 && N >= K)) {
        error("Cannot perform K-means algorithm for this configuration" kMeans_DOWN__1_kMeans_error_use);
        return;
    }

    cv::Mat data(N, dims, CV_32F, data0.ptr(), isrow ? dims * sizeof(float) : static_cast<size_t>(data0.step));
    cv::Mat temp(1, dims, type);

    std::vector<int> counters(K, 0);
    const float* sample = data.ptr<float>(0);

    double max_center_shift = 0;

    for (int k = 0; k < K; ++k) {
        if (counters[k] != 0)
            continue;

        int max_k = 0;
        for (int k1 = 1; k1 < K; ++k1) {
            if (counters[max_k] < counters[k1])
                max_k = k1;
        }

        double max_dist = 0;
        int farthest_i = -1;
        float* new_center = centers.ptr<float>(k);
        float* old_center = centers.ptr<float>(max_k);
        float* _old_center = temp.ptr<float>();
        float scale = 1.f/counters[max_k];
        for (int j = 0; j < dims; ++j)
            _old_center[j] = old_center[j]*scale;

        for (int i = 0; i < N; ++i) {
            sample = data.ptr<float>(i);
            double dist = cv::normL2Sqr_(sample, _old_center, dims);

            if (max_dist <= dist) {
                max_dist = dist;
                farthest_i = i;
            }
        }

        counters[max_k]--;
        counters[k]++;
        sample = data.ptr<float>(farthest_i);

        for (int j = 0; j < dims; ++j) {
            old_center[j] -= sample[j];
            new_center[j] += sample[j];
        }
    }

    for (int k = 0; k < K; ++k) {
        float* center = centers.ptr<float>(k);
        if (counters[k] == 0) {
            error("For some reason one of the clusters is empty" kMeans_DOWN__1_kMeans_error_use);
            return;
        }
        float scale = 1.f/counters[k];
        for (int j = 0; j < dims; ++j)
            center[j] *= scale;

        double dist = 0;
        const float* old_center = old_centers.ptr<float>(k);
        for (int j = 0; j < dims; ++j) {
            double t = center[j] - old_center[j];
            dist += t * t;
        }
        max_center_shift = std::max(max_center_shift, dist);
    }

    std::vector<std::vector<double>> _centers;
    centers.copyTo(_centers);
    if (max_center_shift <= epsilon) {
        result(_centers kMeans_DOWN__1_kMeans_result_use);
    } else {
        _1_loop(img, _centers, K, epsilon kMeans_DOWN__1_kMeans_loop_use);
    }
}
示例#2
0
double cv::kmeans( InputArray _data, int K,
                   InputOutputArray _bestLabels,
                   TermCriteria criteria, int attempts,
                   int flags, OutputArray _centers )
{
    const int SPP_TRIALS = 3;
    Mat data0 = _data.getMat();
    bool isrow = data0.rows == 1;
    int N = isrow ? data0.cols : data0.rows;
    int dims = (isrow ? 1 : data0.cols)*data0.channels();
    int type = data0.depth();

    attempts = std::max(attempts, 1);
    CV_Assert( data0.dims <= 2 && type == CV_32F && K > 0 );
    CV_Assert( N >= K );

    Mat data(N, dims, CV_32F, data0.ptr(), isrow ? dims * sizeof(float) : static_cast<size_t>(data0.step));

    _bestLabels.create(N, 1, CV_32S, -1, true);

    Mat _labels, best_labels = _bestLabels.getMat();
    if( flags & CV_KMEANS_USE_INITIAL_LABELS )
    {
        CV_Assert( (best_labels.cols == 1 || best_labels.rows == 1) &&
                   best_labels.cols*best_labels.rows == N &&
                   best_labels.type() == CV_32S &&
                   best_labels.isContinuous());
        best_labels.copyTo(_labels);
    }
    else
    {
        if( !((best_labels.cols == 1 || best_labels.rows == 1) &&
                best_labels.cols*best_labels.rows == N &&
                best_labels.type() == CV_32S &&
                best_labels.isContinuous()))
            best_labels.create(N, 1, CV_32S);
        _labels.create(best_labels.size(), best_labels.type());
    }
    int* labels = _labels.ptr<int>();

    Mat centers(K, dims, type), old_centers(K, dims, type), temp(1, dims, type);
    std::vector<int> counters(K);
    std::vector<Vec2f> _box(dims);
    Vec2f* box = &_box[0];
    double best_compactness = DBL_MAX, compactness = 0;
    RNG& rng = theRNG();
    int a, iter, i, j, k;

    if( criteria.type & TermCriteria::EPS )
        criteria.epsilon = std::max(criteria.epsilon, 0.);
    else
        criteria.epsilon = FLT_EPSILON;
    criteria.epsilon *= criteria.epsilon;

    if( criteria.type & TermCriteria::COUNT )
        criteria.maxCount = std::min(std::max(criteria.maxCount, 2), 100);
    else
        criteria.maxCount = 100;

    if( K == 1 )
    {
        attempts = 1;
        criteria.maxCount = 2;
    }

    const float* sample = data.ptr<float>(0);
    for( j = 0; j < dims; j++ )
        box[j] = Vec2f(sample[j], sample[j]);

    for( i = 1; i < N; i++ )
    {
        sample = data.ptr<float>(i);
        for( j = 0; j < dims; j++ )
        {
            float v = sample[j];
            box[j][0] = std::min(box[j][0], v);
            box[j][1] = std::max(box[j][1], v);
        }
    }

    for( a = 0; a < attempts; a++ )
    {
        double max_center_shift = DBL_MAX;
        for( iter = 0;; )
        {
            swap(centers, old_centers);

            if( iter == 0 && (a > 0 || !(flags & KMEANS_USE_INITIAL_LABELS)) )
            {
                if( flags & KMEANS_PP_CENTERS )
                    generateCentersPP(data, centers, K, rng, SPP_TRIALS);
                else
                {
                    for( k = 0; k < K; k++ )
                        generateRandomCenter(_box, centers.ptr<float>(k), rng);
                }
            }
            else
            {
                if( iter == 0 && a == 0 && (flags & KMEANS_USE_INITIAL_LABELS) )
                {
                    for( i = 0; i < N; i++ )
                        CV_Assert( (unsigned)labels[i] < (unsigned)K );
                }

                // compute centers
                centers = Scalar(0);
                for( k = 0; k < K; k++ )
                    counters[k] = 0;

                for( i = 0; i < N; i++ )
                {
                    sample = data.ptr<float>(i);
                    k = labels[i];
                    float* center = centers.ptr<float>(k);
                    j=0;
#if CV_ENABLE_UNROLLED
                    for(; j <= dims - 4; j += 4 )
                    {
                        float t0 = center[j] + sample[j];
                        float t1 = center[j+1] + sample[j+1];

                        center[j] = t0;
                        center[j+1] = t1;

                        t0 = center[j+2] + sample[j+2];
                        t1 = center[j+3] + sample[j+3];

                        center[j+2] = t0;
                        center[j+3] = t1;
                    }
#endif
                    for( ; j < dims; j++ )
                        center[j] += sample[j];
                    counters[k]++;
                }

                if( iter > 0 )
                    max_center_shift = 0;

                for( k = 0; k < K; k++ )
                {
                    if( counters[k] != 0 )
                        continue;

                    // if some cluster appeared to be empty then:
                    //   1. find the biggest cluster
                    //   2. find the farthest from the center point in the biggest cluster
                    //   3. exclude the farthest point from the biggest cluster and form a new 1-point cluster.
                    int max_k = 0;
                    for( int k1 = 1; k1 < K; k1++ )
                    {
                        if( counters[max_k] < counters[k1] )
                            max_k = k1;
                    }

                    double max_dist = 0;
                    int farthest_i = -1;
                    float* new_center = centers.ptr<float>(k);
                    float* old_center = centers.ptr<float>(max_k);
                    float* _old_center = temp.ptr<float>(); // normalized
                    float scale = 1.f/counters[max_k];
                    for( j = 0; j < dims; j++ )
                        _old_center[j] = old_center[j]*scale;

                    for( i = 0; i < N; i++ )
                    {
                        if( labels[i] != max_k )
                            continue;
                        sample = data.ptr<float>(i);
                        double dist = normL2Sqr(sample, _old_center, dims);

                        if( max_dist <= dist )
                        {
                            max_dist = dist;
                            farthest_i = i;
                        }
                    }

                    counters[max_k]--;
                    counters[k]++;
                    labels[farthest_i] = k;
                    sample = data.ptr<float>(farthest_i);

                    for( j = 0; j < dims; j++ )
                    {
                        old_center[j] -= sample[j];
                        new_center[j] += sample[j];
                    }
                }

                for( k = 0; k < K; k++ )
                {
                    float* center = centers.ptr<float>(k);
                    CV_Assert( counters[k] != 0 );

                    float scale = 1.f/counters[k];
                    for( j = 0; j < dims; j++ )
                        center[j] *= scale;

                    if( iter > 0 )
                    {
                        double dist = 0;
                        const float* old_center = old_centers.ptr<float>(k);
                        for( j = 0; j < dims; j++ )
                        {
                            double t = center[j] - old_center[j];
                            dist += t*t;
                        }
                        max_center_shift = std::max(max_center_shift, dist);
                    }
                }
            }

            if( ++iter == MAX(criteria.maxCount, 2) || max_center_shift <= criteria.epsilon )
                break;

            // assign labels
            Mat dists(1, N, CV_64F);
            double* dist = dists.ptr<double>(0);
            parallel_for_(Range(0, N),
                          KMeansDistanceComputer(dist, labels, data, centers));
            compactness = 0;
            for( i = 0; i < N; i++ )
            {
                compactness += dist[i];
            }
        }

        if( compactness < best_compactness )
        {
            best_compactness = compactness;
            if( _centers.needed() )
                centers.copyTo(_centers);
            _labels.copyTo(best_labels);
        }
    }

    return best_compactness;
}