K近邻算法

这个算法首先贮藏所有的训练样本，然後通过分析（包括选举，计算加权和等方式）一个新样本周围K个最近邻以给出该样本的相应值。这种方法有时候被称作“基于样本的学习”，即为了预测，我们对于给定的输入搜索最近的已知其相应的特征向量。

数据挖掘研究院

数据挖掘研究院

CvKNearest

K近邻类

数据挖掘研究院

class CvKNearest : public CvStatModel //继承自ML库中的统计模型基类
{
public:

    CvKNearest();
    virtual ~CvKNearest();  //虚函数定义

    CvKNearest( const CvMat* _train_data, const CvMat* _responses,
                const CvMat* _sample_idx=0, bool _is_regression=false, int max_k=32 );

    virtual bool train( const CvMat* _train_data, const CvMat* _responses,
                        const CvMat* _sample_idx=0, bool is_regression=false,
                        int _max_k=32, bool _update_base=false );

    virtual float find_nearest( const CvMat* _samples, int k, CvMat* results,
        const float** neighbors=0, CvMat* neighbor_responses=0, CvMat* dist=0 ) const;

    virtual void clear();
    int get_max_k() const;
    int get_var_count() const;
    int get_sample_count() const;
    bool is_regression() const;

protected:
    ...
};
 
数据挖掘研究院
 

CvKNearest::train

训练KNN模型 数据挖掘研究院

bool CvKNearest::train( const CvMat* _train_data, const CvMat* _responses,
                        const CvMat* _sample_idx=0, bool is_regression=false,
                        int _max_k=32, bool _update_base=false );
 
数据挖掘研究院
 

这个类的方法训练K近邻模型。它遵循一个一般训练方法约定的限制：只支持CV_ROW_SAMPLE数据格式，输入向量必须都是有序的，而输出可以是 无序的(当is_regression=false)，可以是有序的（is_regression=true）。并且变量子集和省略度量是不被支持的。

参数_max_k 指定了最大邻居的个数，它将被传给方法find_nearest。参数 _update_base 指定模型是由原来的数据训练(_update_base=false)，还是被新训练数据更新後再训练(_update_base=true）。在後一种情况下_max_k 不能大于原值, 否则它会被忽略. 数据挖掘研究院

CvKNearest::find_nearest

寻找输入向量的最近邻

float CvKNearest::find_nearest( const CvMat* _samples, int k, CvMat* results=0,
        const float** neighbors=0, CvMat* neighbor_responses=0, CvMat* dist=0 ) const;
 
数据挖掘实验室
 

For each input vector (which are rows of the matrix _samples) the method finds k≤get_max_k() nearest neighbor. In case of regression, the predicted result will be a mean value of the particular vector's neighbor responses. In case of classification the class is determined by voting. 数据挖掘研究院

For custom classification/regression prediction, the method can optionally return pointers to the neighbor vectors themselves (neighbors, array of k*_samples->rows pointers), their corresponding output values (neighbor_responses, a vector of k*_samples->rows elements) and the distances from the input vectors to the neighbors (dist, also a vector of k*_samples->rows elements). 数据挖掘研究院

For each input vector the neighbors are sorted by their distances to the vector.

数据挖掘研究院

In case of a single input vector all the output matrices are optional and the predicted value is returned by the method.

数据挖掘实验室

例程：使用kNN进行2维样本集的分类，样本集的分布为混合高斯分布

#include "ml.h"
#include "highgui.h"

int main( int argc, char** argv )
{
    const int K = 10;
    int i, j, k, accuracy;
    float response;
    int train_sample_count = 100;
    CvRNG rng_state = cvRNG(-1);
    CvMat* trainData = cvCreateMat( train_sample_count, 2, CV_32FC1 );
    CvMat* trainClasses = cvCreateMat( train_sample_count, 1, CV_32FC1 );
    IplImage* img = cvCreateImage( cvSize( 500, 500 ), 8, 3 );
    float _sample[2];
    CvMat sample = cvMat( 1, 2, CV_32FC1, _sample );
    cvZero( img );

    CvMat trainData1, trainData2, trainClasses1, trainClasses2;

    // form the training samples
    cvGetRows( trainData, &trainData1, 0, train_sample_count/2 );
    cvRandArr( &rng_state, &trainData1, CV_RAND_NORMAL, cvScalar(200,200), cvScalar(50,50) );

    cvGetRows( trainData, &trainData2, train_sample_count/2, train_sample_count );
    cvRandArr( &rng_state, &trainData2, CV_RAND_NORMAL, cvScalar(300,300), cvScalar(50,50) );

    cvGetRows( trainClasses, &trainClasses1, 0, train_sample_count/2 );
    cvSet( &trainClasses1, cvScalar(1) );

    cvGetRows( trainClasses, &trainClasses2, train_sample_count/2, train_sample_count );
    cvSet( &trainClasses2, cvScalar(2) );

    // learn classifier
    CvKNearest knn( trainData, trainClasses, 0, false, K );
    CvMat* nearests = cvCreateMat( 1, K, CV_32FC1);

    for( i = 0; i < img->height; i++ )
    {
        for( j = 0; j < img->width; j++ )
        {
            sample.data.fl[0] = (float)j;
            sample.data.fl[1] = (float)i;

            // estimates the response and get the neighbors' labels
            response = knn.find_nearest(&sample,K,0,0,nearests,0);

            // compute the number of neighbors representing the majority
            for( k = 0, accuracy = 0; k < K; k++ )
            {
                if( nearests->data.fl[k] == response)
                    accuracy++;
            }
            // highlight the pixel depending on the accuracy (or confidence)
            cvSet2D( img, i, j, response == 1 ?
                (accuracy > 5 ? CV_RGB(180,0,0) : CV_RGB(180,120,0)) :
                (accuracy > 5 ? CV_RGB(0,180,0) : CV_RGB(120,120,0)) );
        }
    }

    // display the original training samples
    for( i = 0; i < train_sample_count/2; i++ )
    {
        CvPoint pt;
        pt.x = cvRound(trainData1.data.fl[i*2]);
        pt.y = cvRound(trainData1.data.fl[i*2+1]);
        cvCircle( img, pt, 2, CV_RGB(255,0,0), CV_FILLED );
        pt.x = cvRound(trainData2.data.fl[i*2]);
        pt.y = cvRound(trainData2.data.fl[i*2+1]);
        cvCircle( img, pt, 2, CV_RGB(0,255,0), CV_FILLED );
    }

    cvNamedWindow( "classifier result", 1 );
    cvShowImage( "classifier result", img );
    cvWaitKey(0);

    cvReleaseMat( &trainClasses );
    cvReleaseMat( &trainData );
    return 0;
}
 
数据挖掘研究院