前一段儿想用opencv做一下数字识别,用神经网络做识别。
在网上搜了一下关于opencv中ANN的使用方法,@小魏的修行路 的【模式识别】OpenCV中使用神经网络 CvANN_MLP 这篇文章写得挺好,照搬里面的例程运行了一下,发现有些错误,而且从他最后的结果图片来看明显是分类分错了。但是他的这篇博文还是写的挺好的,简单,通俗易懂。关于OPENCV中神经网络相关的使用方法这里就不作介绍了,大家可以直接看他的博客。
这里说一下例程的简单思路:
1.首先定义两种类型的若干个点,
2.然后利用这些样本点训练出一个模型,
3.新建一张图片,使用图片中的每一个像素作为测试点,利用上一步训练出的模型把这些像素分为两类,并用不同的颜色标记出来。
这里是程序运行的结果:
以下源码只是对 @小魏的修行路 的程序作了小部分改动:
源码
//编程环境:VS2010 + Opencv2.4.8
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/ml/ml.hpp>
#include <iostream>
#include <string>
using namespace std;
using namespace cv;
int main()
{
//Setup the BPNetwork
CvANN_MLP bp;
// Set up BPNetwork's parameters
CvANN_MLP_TrainParams params;
params.train_method=CvANN_MLP_TrainParams::BACKPROP; //(Back Propagation,BP)反向传播算法
params.bp_dw_scale=0.1;
params.bp_moment_scale=0.1;
// Set up training data
float labels[10][2] = {{0.9,0.1},{0.1,0.9},{0.9,0.1},{0.1,0.9},{0.9,0.1},{0.9,0.1},{0.1,0.9},{0.1,0.9},{0.9,0.1},{0.9,0.1}};
//这里对于样本标记为0.1和0.9而非0和1,主要是考虑到sigmoid函数的输出为一般为0和1之间的数,只有在输入趋近于-∞和+∞才逐渐趋近于0和1,而不可能达到。
Mat labelsMat(10, 2, CV_32FC1, labels);
float trainingData[10][2] = { {11,12},{111,112}, {21,22}, {211,212},{51,32}, {71,42}, {441,412},{311,312}, {41,62}, {81,52} };
Mat trainingDataMat(10, 2, CV_32FC1, trainingData);
Mat layerSizes=(Mat_<int>(1,5) << 2, 2, 2, 2, 2); //5层:输入层,3层隐藏层和输出层,每层均为两个perceptron
bp.create(layerSizes,CvANN_MLP::SIGMOID_SYM);//CvANN_MLP::SIGMOID_SYM ,选用sigmoid作为激励函数
bp.train(trainingDataMat, labelsMat, Mat(),Mat(), params); //训练
// Data for visual representation
int width = 512, height = 512;
Mat image = Mat::zeros(height, width, CV_8UC3);
Vec3b green(0,255,0), blue (255,0,0);
// Show the decision regions
for (int i = 0; i < image.rows; ++i)
{
for (int j = 0; j < image.cols; ++j)
{
Mat sampleMat = (Mat_<float>(1,2) << i,j);
Mat responseMat;
bp.predict(sampleMat,responseMat);
float* p=responseMat.ptr<float>(0);
//
if (p[0] > p[1])
{
image.at<Vec3b>(j, i) = green;
}
else
{
image.at<Vec3b>(j, i) = blue;
}
}
}
// Show the training data
int thickness = -1;
int lineType = 8;
circle( image, Point(111, 112), 5, Scalar( 0, 0, 0), thickness, lineType);
circle( image, Point(211, 212), 5, Scalar( 0, 0, 0), thickness, lineType);
circle( image, Point(441, 412), 5, Scalar( 0, 0, 0), thickness, lineType);
circle( image, Point(311, 312), 5, Scalar( 0, 0, 0), thickness, lineType);
circle( image, Point(11, 12), 5, Scalar(255, 255, 255), thickness, lineType);
circle( image, Point(21, 22), 5, Scalar(255, 255, 255), thickness, lineType);
circle( image, Point(51, 32), 5, Scalar(255, 255, 255), thickness, lineType);
circle( image, Point(71, 42), 5, Scalar(255, 255, 255), thickness, lineType);
circle( image, Point(41, 62), 5, Scalar(255, 255, 255), thickness, lineType);
circle( image, Point(81, 52), 5, Scalar(255, 255, 255), thickness, lineType);
imwrite("result.png", image); // save the image
imshow("BP Simple Example", image); // show it to the user
waitKey(0);
return 0;
}