利用opencv源代码和vs编程序训练分类器haartraining.cpp

如需转载请注明本博网址：http://blog.csdn.net/ding977921830/article/details/47733363。

一  训练框架

训练人脸检測分类器须要三个步骤：

(1) 准备正负样本集，分别放到两个目录里。

我使用的是麻省理工的那个人脸库。大家能够网上搜一下。

（2）把正样本集生成正样本描写叙述文件（*.vec），把负样本集生成负样本集合文件。详细怎么操作请參考我博客中的另外两篇文章，各自是http://blog.csdn.net/ding977921830/article/details/45913789和http://blog.csdn.net/ding977921830/article/details/45914137。

（3）利用........\opencv\sources\apps\haartraining\haartraining.cpp训练分类器。

二  建立project

我使用的是vs2012和opencv2.4.9，事实上，使用其它的版本号也区别不多大。

1  配置opencv2.4.9和vs2012，这个网上有非常多资料，我就不啰嗦了哈。

2  在vs中新建project，把opencv库中的以下文件........\opencv\sources\apps\haartraining加入到project中，在解决方式资源管理器中，分别加入头文件和源文件，加入好后，内容例如以下：

三  程序

上面main.cpp的内容也就是haartraining.cpp中的程序，详细内容例如以下：

//M*/

/*
 * haartraining.cpp
 *里面有部分參数我是稍作改动
 *<a target=_blank href="http://blog.csdn.net/ding977921830/article/details/47733363">http://blog.csdn.net/ding977921830/article/details/47733363</a>
 * Train cascade classifier
 */

#include <cstdio>
#include <cstring>
#include <cstdlib>

using namespace std;

#include "cvhaartraining.h"

int main( int argc, char* argv[] )
{
    int i = 0;
    char* nullname = (char*)"(NULL)";

    char* vecname = NULL;
    char* dirname = NULL;
    char* bgname  = NULL;

    bool bg_vecfile = false;
    int npos    = 2000;   //保证npos与nneg的比例为1:2至1：：3之间比較好
    int nneg    = 4000;
    int nstages = 3;      //为了节约时间能够把把设置为1，或2或3。当然也能够设置十几或二十几。只是，我没有耐心实验
    int mem     = 200;
    int nsplits = 1;
    float minhitrate     = 0.995F;
    float maxfalsealarm  = 0.5F;
    float weightfraction = 0.95F;
    int mode         = 0;
    int symmetric    = 1;
    int equalweights = 0;
    int width  = 20;
    int height = 20;
    const char* boosttypes[] = { "DAB", "RAB", "LB", "GAB" };
    int boosttype = 0;    //选用DAB
    const char* stumperrors[] = { "misclass", "gini", "entropy" };
    int stumperror = 0;   //选用misclass
    int maxtreesplits = 0;
    int minpos = 500;

    if( argc == 1 )
    {
        printf( "Usage: %s\n  -data <dir_name>\n"
                "  -vec <vec_file_name>\n"
                "  -bg <background_file_name>\n"
                "  [-bg-vecfile]\n"
                "  [-npos <number_of_positive_samples = %d>]\n"
                "  [-nneg <number_of_negative_samples = %d>]\n"
                "  [-nstages <number_of_stages = %d>]\n"
                "  [-nsplits <number_of_splits = %d>]\n"
                "  [-mem <memory_in_MB = %d>]\n"
                "  [-sym (default)] [-nonsym]\n"
                "  [-minhitrate <min_hit_rate = %f>]\n"
                "  [-maxfalsealarm <max_false_alarm_rate = %f>]\n"
                "  [-weighttrimming <weight_trimming = %f>]\n"
                "  [-eqw]\n"
                "  [-mode <BASIC (default) | CORE | ALL>]\n"
                "  [-w <sample_width = %d>]\n"
                "  [-h <sample_height = %d>]\n"
                "  [-bt <DAB | RAB | LB | GAB (default)>]\n"
                "  [-err <misclass (default) | gini | entropy>]\n"
                "  [-maxtreesplits <max_number_of_splits_in_tree_cascade = %d>]\n"
                "  [-minpos <min_number_of_positive_samples_per_cluster = %d>]\n",
                argv[0], npos, nneg, nstages, nsplits, mem,
                minhitrate, maxfalsealarm, weightfraction, width, height,
                maxtreesplits, minpos );

        return 0;
    }

    for( i = 1; i < argc; i++ )
    {
       /*if( !strcmp( argv[i], "-data" ) )
        {
            dirname = argv[++i];
        }
        else if( !strcmp( argv[i], "-vec" ) )
        {
            vecname = argv[++i];
        }
        else if( !strcmp( argv[i], "-bg" ) )
        {
            bgname = argv[++i];
        }*/
		 if( !strcmp( argv[i], "-data" ) )    //前面这三个条件里面的内容我稍作改动
        {
            dirname = argv[i];
        }
        else if( !strcmp( argv[i], "-vec.vec" ) )
        {
            vecname = argv[i];
        }
        else if( !strcmp( argv[i], "-bg.txt" ) )
        {
            bgname = argv[i];
        }
        else if( !strcmp( argv[i], "-bg-vecfile" ) )
        {
            bg_vecfile = true;
        }
        else if( !strcmp( argv[i], "-npos" ) )
        {
            npos = atoi( argv[++i] );
        }
        else if( !strcmp( argv[i], "-nneg" ) )
        {
            nneg = atoi( argv[++i] );
        }
        else if( !strcmp( argv[i], "-nstages" ) )
        {
            nstages = atoi( argv[++i] );
        }
        else if( !strcmp( argv[i], "-nsplits" ) )
        {
            nsplits = atoi( argv[++i] );
        }
        else if( !strcmp( argv[i], "-mem" ) )
        {
            mem = atoi( argv[++i] );
        }
        else if( !strcmp( argv[i], "-sym" ) )
        {
            symmetric = 1;
        }
        else if( !strcmp( argv[i], "-nonsym" ) )
        {
            symmetric = 0;
        }
        else if( !strcmp( argv[i], "-minhitrate" ) )
        {
            minhitrate = (float) atof( argv[++i] );
        }
        else if( !strcmp( argv[i], "-maxfalsealarm" ) )
        {
            maxfalsealarm = (float) atof( argv[++i] );
        }
        else if( !strcmp( argv[i], "-weighttrimming" ) )
        {
            weightfraction = (float) atof( argv[++i] );
        }
        else if( !strcmp( argv[i], "-eqw" ) )
        {
            equalweights = 1;
        }
        else if( !strcmp( argv[i], "-mode" ) )
        {
            char* tmp = argv[++i];

            if( !strcmp( tmp, "CORE" ) )
            {
                mode = 1;
            }
            else if( !strcmp( tmp, "ALL" ) )
            {
                mode = 2;
            }
            else
            {
                mode = 0;
            }
        }
        else if( !strcmp( argv[i], "-w" ) )
        {
            width = atoi( argv[++i] );
        }
        else if( !strcmp( argv[i], "-h" ) )
        {
            height = atoi( argv[++i] );
        }
        else if( !strcmp( argv[i], "-bt" ) )
        {
            i++;
            if( !strcmp( argv[i], boosttypes[0] ) )
            {
                boosttype = 0;
            }
            else if( !strcmp( argv[i], boosttypes[1] ) )
            {
                boosttype = 1;
            }
            else if( !strcmp( argv[i], boosttypes[2] ) )
            {
                boosttype = 2;
            }
            else
            {
                boosttype = 3;
            }
        }
        else if( !strcmp( argv[i], "-err" ) )
        {
            i++;
            if( !strcmp( argv[i], stumperrors[0] ) )
            {
                stumperror = 0;
            }
            else if( !strcmp( argv[i], stumperrors[1] ) )
            {
                stumperror = 1;
            }
            else
            {
                stumperror = 2;
            }
        }
        else if( !strcmp( argv[i], "-maxtreesplits" ) )
        {
            maxtreesplits = atoi( argv[++i] );
        }
        else if( !strcmp( argv[i], "-minpos" ) )
        {
            minpos = atoi( argv[++i] );
        }
    }

    printf( "Data dir name: %s\n", ((dirname == NULL) ? nullname : dirname ) );
    printf( "Vec file name: %s\n", ((vecname == NULL) ? nullname : vecname ) );
    printf( "BG  file name: %s, is a vecfile: %s\n", ((bgname == NULL) ? nullname : bgname ), bg_vecfile ? "yes" : "no" );
    printf( "Num pos: %d\n", npos );
    printf( "Num neg: %d\n", nneg );
    printf( "Num stages: %d\n", nstages );
    printf( "Num splits: %d (%s as weak classifier)\n", nsplits,
        (nsplits == 1) ?

"stump" : "tree" );
    printf( "Mem: %d MB\n", mem );
    printf( "Symmetric: %s\n", (symmetric) ? "TRUE" : "FALSE" );
    printf( "Min hit rate: %f\n", minhitrate );
    printf( "Max false alarm rate: %f\n", maxfalsealarm );
    printf( "Weight trimming: %f\n", weightfraction );
    printf( "Equal weights: %s\n", (equalweights) ? "TRUE" : "FALSE" );
    printf( "Mode: %s\n", ( (mode == 0) ? "BASIC" : ( (mode == 1) ? "CORE" : "ALL") ) );
    printf( "Width: %d\n", width );
    printf( "Height: %d\n", height );
    //printf( "Max num of precalculated features: %d\n", numprecalculated );
    printf( "Applied boosting algorithm: %s\n", boosttypes[boosttype] );
    printf( "Error (valid only for Discrete and Real AdaBoost): %s\n",
            stumperrors[stumperror] );

    printf( "Max number of splits in tree cascade: %d\n", maxtreesplits );
    printf( "Min number of positive samples per cluster: %d\n", minpos );

    cvCreateTreeCascadeClassifier( dirname, vecname, bgname,
                               npos, nneg, nstages, mem,
                               nsplits,
                               minhitrate, maxfalsealarm, weightfraction,
                               mode, symmetric,
                               equalweights, width, height,
                               boosttype, stumperror,
                               maxtreesplits, minpos, bg_vecfile );

    return 0;
}

我的命令行參数为："D:\vs2012\projects\train_opencv_main\train_cascade\Debug\test.exe" "-data"  "-vec.vec"  "-bg.txt"

。详细设置方法是  调试----属性----配置属性----调试---命令參数

watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQv/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center" alt="">

1 注意命令行參数中间要有空格的。

2 当中第一个你要改动为你自己电脑上project的绝对路径；

3 "-data" 是存放训练好的分类器，须要预先建立好一个的空目录。

4 "-vec.vec" 是我的正样本描写叙述文件。

5 "-bg.txt"是我的负样本集合文件。

四  训练结果

1  dos操作窗体

2  data目录的内容为：

我的0文件里训练了6个弱文类器。1文件里含有9个弱分类器。2目录下有17个弱分类器，每个目录就是一个级联stage。显然是越来越复杂的哈。

3  以文件0为例，里面的内容为：

6

1

2

7 1 6 10 0 -1

9 1 2 10 0 3

haar_x3

4.792333e-002 0 -1

-1.845703e+000 1.845703e+000

1

2

1 3 18 12 0 -1

1 7 18 4 0 3

haar_y3

2.389797e-001 0 -1

-1.396623e+000 1.396623e+000

1

3

2 16 6 4 0 -1

2 16 3 2 0 2

5 18 3 2 0 2

haar_x2_y2

6.900427e-003 0 -1

-9.798445e-001 9.798445e-001

1

2

10 0 10 1 0 -1

10 0 5 1 0 2

haar_x2

1.219139e-002 0 -1

-5.156118e-001 5.156118e-001

1

2

0 0 10 1 0 -1

5 0 5 1 0 2

haar_x2

1.014664e-002 0 -1

-7.365732e-001 7.365732e-001

1

2

9 14 5 3 0 -1

9 15 5 1 0 3

haar_y3

-6.578934e-003 0 -1

7.885281e-001 -7.885281e-001

-3.758514e+000



-1

-1

4  xml文件

到这里我们的训练分类器最终出来的，XML文件能够在在vs中直接调用了。xml文件的内容你看是跟上面data文件里的内容是严格一一相应的，我摘录当中部分内容（也就是0目录部分）例如以下：

<?xml version="1.0"?>

<opencv_storage>

<_-data type_id="opencv-haar-classifier">

  <size>

    20 20</size>

  <stages>

    <_>

      <!-- stage 0 -->

      <trees>

        <_>

          <!-- tree 0 -->

          <_>

            <!-- root node -->

            <feature>

              <rects>

                <_>

                  7 1 6 10 -1.</_>

                <_>

                  9 1 2 10 3.</_></rects>

              <tilted>0</tilted></feature>

            <threshold>4.7923330217599869e-002</threshold>

            <left_val>-1.8457030057907104e+000</left_val>

            <right_val>1.8457030057907104e+000</right_val></_></_>

        <_>

          <!-- tree 1 -->

          <_>

            <!-- root node -->

            <feature>

              <rects>

                <_>

                  1 3 18 12 -1.</_>

                <_>

                  1 7 18 4 3.</_></rects>

              <tilted>0</tilted></feature>

            <threshold>2.3897969722747803e-001</threshold>

            <left_val>-1.3966230154037476e+000</left_val>

            <right_val>1.3966230154037476e+000</right_val></_></_>

        <_>

          <!-- tree 2 -->

          <_>

            <!-- root node -->

            <feature>

              <rects>

                <_>

                  2 16 6 4 -1.</_>

                <_>

                  2 16 3 2 2.</_>

                <_>

                  5 18 3 2 2.</_></rects>

              <tilted>0</tilted></feature>

            <threshold>6.9004269316792488e-003</threshold>

            <left_val>-9.7984451055526733e-001</left_val>

            <right_val>9.7984451055526733e-001</right_val></_></_>

        <_>

          <!-- tree 3 -->

          <_>

            <!-- root node -->

            <feature>

              <rects>

                <_>

                  10 0 10 1 -1.</_>

                <_>

                  10 0 5 1 2.</_></rects>

              <tilted>0</tilted></feature>

            <threshold>1.2191389687359333e-002</threshold>

            <left_val>-5.1561182737350464e-001</left_val>

            <right_val>5.1561182737350464e-001</right_val></_></_>

        <_>

          <!-- tree 4 -->

          <_>

            <!-- root node -->

            <feature>

              <rects>

                <_>

                  0 0 10 1 -1.</_>

                <_>

                  5 0 5 1 2.</_></rects>

              <tilted>0</tilted></feature>

            <threshold>1.0146640241146088e-002</threshold>

            <left_val>-7.3657321929931641e-001</left_val>

            <right_val>7.3657321929931641e-001</right_val></_></_>

        <_>

          <!-- tree 5 -->

          <_>

            <!-- root node -->

            <feature>

              <rects>

                <_>

                  9 14 5 3 -1.</_>

                <_>

                  9 15 5 1 3.</_></rects>

              <tilted>0</tilted></feature>

            <threshold>-6.5789339132606983e-003</threshold>

            <left_val>7.8852808475494385e-001</left_val>

            <right_val>-7.8852808475494385e-001</right_val></_></_></trees>

      <stage_threshold>-3.7585139274597168e+000</stage_threshold>

      <parent>-1</parent>

      <next>-1</next></_>

    <_>