OpenCV——手势识别

使用ANN神经网络训练数据后进行手势识别。

#include "header.h"

int main()

{

    const int sample_num = ;              //训练每类图片数量

    const int class_num = ;                //训练类数3:石头剪刀布

    const int image_cols = ;

    const int image_rows = ;

    string  Name, Path;

    float trainingData[class_num * sample_num][image_cols * image_rows] = { {  } };       //每一行一个训练样本

    float labels[class_num * sample_num][class_num] = { {  } };                           //训练样本标签

    cout << "training Data.........\n";

    for (int i = ; i < class_num; i++){

        int j = ;

        Path = getstring(i + ) + "/" + "*.*";

        HANDLE hFile;

        LPCTSTR lp = StringToWchar(Path);

        WIN32_FIND_DATA pNextInfo;

        hFile = FindFirstFile(lp, &pNextInfo);

        if (hFile == INVALID_HANDLE_VALUE){

            cout << "failed" << endl;

            exit(-);//搜索失败

        }

        cout << "folder name:" << i +  << endl;

        do{

            //必须加这句，不然会加载.和..的文件而加载不了图片，

            if (pNextInfo.cFileName[] == '.')continue;

            cout << "file name" << WcharToChar(pNextInfo.cFileName) << endl;

            Mat srcImage = imread(getstring(i+) + "/" + WcharToChar(pNextInfo.cFileName), CV_LOAD_IMAGE_GRAYSCALE);

            Mat trainImage;

            //if (!srcImage.empty())cout << " done \n";

            //处理样本图像

            resize(srcImage, trainImage, Size(image_cols, image_rows), (, ), (, ), CV_INTER_AREA);

            Canny(trainImage, trainImage, , , , false);

            for (int k = ; k < image_rows * image_cols; k++){

                //cout << "矩阵 k-- " << k << "   j--" << j << "   i--" << i << endl;

                trainingData[i*sample_num + j][k] = (float)trainImage.data[k];

            }

            j++;

        } while (FindNextFile(hFile, &pNextInfo));

    }

    // 训练好的矩阵

    Mat DataMat(class_num*sample_num, image_rows*image_cols, CV_32FC1, trainingData);

    cout << "DataMat   done~" << endl;

    // 初始化标签

    // 0-石头 1-剪刀 2-布

    for (int i = ; i < class_num ; i++){

        for (int j = ; j < sample_num; j++){

            for (int k = ; k < class_num; k++){

                if (k == i)labels[i*sample_num + j][k] = ;

                else labels[i*sample_num + j][k] = ;

            }

        }

    }

    // 标签矩阵

    Mat labelsMat(class_num*sample_num, class_num, CV_32FC1, labels);

    cout << "labelsMat  done~" << endl;

    //训练代码

    CvANN_MLP bp;

    CvANN_MLP_TrainParams params;

    params.train_method = CvANN_MLP_TrainParams::BACKPROP;

    params.bp_dw_scale = 0.001;

    params.bp_moment_scale = 0.1;

    //cvTermCriteria 迭代终止规则

    params.term_crit = cvTermCriteria(CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, , 0.0001);

    //设置网络层数

    Mat layerSizes = (Mat_<int>(, ) << image_rows*image_cols, int(image_rows*image_cols / ),

                                                                 int(image_rows*image_cols / ), class_num);

    bp.create(layerSizes, CvANN_MLP::SIGMOID_SYM, 1.0, 1.0);

    cout << "training...." << endl;

    bp.train(DataMat, labelsMat, Mat(), Mat(), params);

    bp.save("detect_gesture.xml");

    cout << "done" << endl;

    //测试神经网络

    cout << "testing...." << endl;

    Mat test = imread("test.jpg");

    Mat temp;

    resize(test, temp, Size(image_cols, image_rows), (, ), (, ), CV_INTER_AREA);

    Canny(temp, temp, , , , false);

    Mat_<float>sample(, image_rows*image_cols);

    for (int i = ; i<image_rows*image_cols; ++i){

        sample.at<float>(, i) = (float)temp.data[i];

    }

    Mat result;

    bp.predict(sample, result);

    float* p = result.ptr<float>();

    float max = -, min = ;

    int index = ;

    for (int i = ; i<class_num; i++)

    {

        cout << (float)(*(p + i)) << " ";

        if (i == class_num - )

            cout << endl;

        if ((float)(*(p + i))>max)

        {

            min = max;

            max = (float)(*(p + i));

            index = i;

        }

        else

        {

            if (min < (float)(*(p + i)))

                min = (float)(*(p + i));

        }

    }

    cout << "Your choice :" << choice[index] << endl << "识别率:"

                                              << (((max - min) * ) >  ?  : ((max - min) * )) << endl;

    //石头剪刀布——游戏开局~

    int computer = random();

    cout << "computer's choice :" << choice[computer] << endl;

    if (computer == index) cout << "A Draw   -_- " << endl << endl;

    else if ((computer < index && (index - computer == )) || (computer ==  && index == )){

        cout << "You Lose  T_T " << endl << endl;

    }

    else cout << "You Win o   *￣▽￣* " << endl << endl;

    system("pause");

    waitKey();

    return ;

}

运行一次后，不用每次都训练数据，直接加载第一次保存的 "detect_gesture.xml"即可

CvANN_MLP bp;

CvANN_MLP_TrainParams params;

bp.load("detect_gesture.xml");

PS:

//CvTermCriteria()

//迭代算法的终止准则

#define CV_TERMCRIT_ITER    1

#define CV_TERMCRIT_NUMBER  CV_TERMCRIT_ITER

#define CV_TERMCRIT_EPS     2

typedef struct CvTermCriteria

 {

  int    type;                      // CV_TERMCRIT_ITER 和CV_TERMCRIT_EPS二值之一，或者二者的组合

  int    max_iter;                  // 最大迭代次数

  double epsilon;                   // 结果的精确性

 }

 CvTermCriteria;

// 构造函数

inline  CvTermCriteria  cvTermCriteria( int type, int max_iter, double epsilon );

// 在满足max_iter和epsilon的条件下检查终止准则并将其转换使得type=CV_TERMCRIT_ITER+CV_TERMCRIT_EPS

CvTermCriteria cvCheckTermCriteria( CvTermCriteria criteria, double default_eps, int default_max_iters );

文件查找相关