机器学习---基于KNN算法的数字手写板识别

图像用的是opencv目录中的：digits.png。每20*20像素为一个数字，图像的大小是2000*1000，一共是5000个数字，用300个作为”训练“数字，2000作为测试数字，KNN算法识别率就是高，作弊测试可以达到95%，盲测可以达到92%。

全部的程序：

#include<opencv2/opencv.hpp>
#include<opencv2/ml/ml.hpp>
#include<fstream>
#include<time.h>
#include<iostream>
#include<stdio.h>
using namespace cv;
using namespace std;
using namespace cv::ml;

#define maxCol 100
#define maxRow 50
#define b 20

ofstream fout;
int main()
{
	Mat src, gray;
	Mat dataMat;
	Mat labelMat;
	fout.open("D:/test.txt");
	src = imread("D:/picture/digits.png");
	if (src.empty())
	{
		cout << "could not load the image" << endl;
		return -1;
	}
	cvtColor(src, gray, COLOR_BGR2GRAY);
	//得到所有的测试数据,检测数据以及对应的标签数据。
	for (int col = 0; col < maxCol; col++)
	{
		for (int row = 0; row < maxRow; row++)
		{
			Mat temp;
			gray(Range(row*b, (row + 1)*b), Range(col*b, (col + 1)*b)).copyTo(temp);
			dataMat.push_back(temp.reshape(0, 1));
			labelMat.push_back((int)(row / 5));
		}
	}
	dataMat.convertTo(dataMat, CV_32F);
	//knn算法实现
	int traingNum = 3000;
	Mat traingDataMat = dataMat(Range(0, traingNum), Range::all());
	Mat trainglabelMat = labelMat(Range(0, traingNum), Range::all());
	KNearest::Params params;
	params.defaultK = 5;
	params.isclassifier = true;
	Ptr<TrainData> knn;
	knn = TrainData::create(traingDataMat, ROW_SAMPLE, trainglabelMat);
	Ptr<KNearest> model;
	model = StatModel::train<KNearest>(knn, params);
	double train = 0;
	double test = 0;
	int samplesNum = 3000;
	for (int i = 0; i < dataMat.rows; i++)
	{
		Mat sample = dataMat.row(i);
		float r = model->predict(sample); //输出预测的 结果
		float r1 = abs(r - labelMat.at<int>(i)) <= FLT_EPSILON ? 1.f : 0.f;
		if (i < traingNum)
			train += r1;
		else
			test += r1;
	}
	test /= dataMat.rows - traingNum;
	train /= traingNum;
	printf("accuracy: train = %.1f%%, test = %.1f%%\n",
		train*100., test*100.);
	waitKey(0);
	getchar();
	return 0;
}