印刷喷码字符识别，数段字符识别：易拉罐底字符识别开发说明书

本系统分为：图像预处理。单易拉罐定位。字符区域块定位，字符识别四大块。

1、图像预处理包含。对不均匀光照的处理，通过直方图拉伸等手段对图像进行亮度区域选择。突出字符区域的亮度分布。

（说明：因为系统实时性的要求，尽量降低预处理过程。

）

2、单易拉罐定位：当一幅图像中出现多个易拉罐的时候，首先要定位到单个易拉罐，分析易拉罐的形状。能够採用基于易拉罐外形的形状匹配思路来定位到单个易拉罐或者採用基于圆检測能够採用hough圆检測或者小波变换的圆检測来定位到单个易拉罐。

3、字符区域块定位：因为字符区域块具有旋转的特点，这里採用形态学的思路。先使字符区域膨胀粘连成一个总体，然后检測轮廓，通过长宽比和面积筛选轮廓，能够确定字符区域块的位置，最后依据字符区域块的轮廓拟合出的矩形的倾斜角度做矫正就能够得到字符区域块的水平矫正后的区域。

4、字符识别：包含单个字符区域的切割，字符样本筛选和处理，字符训练，字符识别。

（1）单个字符的切割：在第三步处理好的倾斜矫正后的图像上。先垂直投影，将字符区域行切割出来；对于单行的字符区域。做水平投影，然后依据字符宽固定的思路做字符切割，切割出单个的字符。

（2）对单个的字符按类别分类好。并对样本进行初步的预处理，增强，归一化。

将全部的样本归一化为28*28区域大小。

（3）採用CNN卷积神经网络对字符进行训练。

本项目採用的卷积结构说明：
第一层仅具有一个特征映射是输入图像本身。在以下的层中，每一个特征映射保持一定数目的独特的内核（权重的二维阵列），等于先前层中的特征映射的数量。在特征图中的每一个内核的大小是同样的，而且是一个设计參数。

在特征图中的像素值是通过卷积其内核与前一层中的对应特征映射推导。

在最后一层的特征映射的数目等于输出选项的数目。比如在0-9数字识别，会有在输出层10的特征图，并具有最高的像素值的特征映射将结果。

#include ".\cnn.h"

#include <stdlib.h>
#include <stdio.h>
#include <time.h> /*用到了time函数，所以要有这个头文件*/

CCNN::CCNN(void)
{
    ConstructNN();
}

CCNN::~CCNN(void)
{
    DeleteNN();
}


#ifndef max
#define max(a,b)            (((a) > (b)) ? (a) : (b))
#endif

////////////////////////////////////
void CCNN::ConstructNN()
////////////////////////////////////
{
    int i;

    m_nLayer = 5;
    m_Layer = new Layer[m_nLayer];

    m_Layer[0].pLayerPrev = NULL;
    for(i=1; i<m_nLayer; i++) m_Layer[i].pLayerPrev = &m_Layer[i-1];

    m_Layer[0].Construct    (   INPUT_LAYER,        1,      29,     0,  0   );
    m_Layer[1].Construct    (   CONVOLUTIONAL,      6,      13,     5,  2   );
    m_Layer[2].Construct    (   CONVOLUTIONAL,      50,     5,      5,  2   );
    m_Layer[3].Construct    (   FULLY_CONNECTED,    100,    1,      5,  1   );
    m_Layer[4].Construct    (   FULLY_CONNECTED,    10,     1,      1,  1   );

}

///////////////////////////////
void CCNN::DeleteNN()
///////////////////////////////
{
    //SaveWeights("weights_updated.txt");
    for(int i=0; i<m_nLayer; i++) m_Layer[i].Delete();
}

//////////////////////////////////////////////
void CCNN::LoadWeightsRandom()
/////////////////////////////////////////////
{
    int i, j, k, m;

    srand((unsigned)time(0));

    for ( i=1; i<m_nLayer; i++ )
    {
        for( j=0; j<m_Layer[i].m_nFeatureMap; j++ )
        {
            m_Layer[i].m_FeatureMap[j].bias = 0.05 * RANDOM_PLUS_MINUS_ONE;

            for(k=0; k<m_Layer[i].pLayerPrev->m_nFeatureMap; k++)
                for(m=0; m < m_Layer[i].m_KernelSize * m_Layer[i].m_KernelSize; m++)    
                    m_Layer[i].m_FeatureMap[j].kernel[k][m] = 0.05 * RANDOM_PLUS_MINUS_ONE;
        }
    }
}
//////////////////////////////////////////////
void CCNN::LoadWeights(char *FileName)
/////////////////////////////////////////////
{
    int i, j, k, m, n;

    FILE *f;
    if((f = fopen(FileName, "r")) == NULL) return;

    for ( i=1; i<m_nLayer; i++ )
    {
        for( j=0; j<m_Layer[i].m_nFeatureMap; j++ )
        {
            fscanf(f, "%lg ", &m_Layer[i].m_FeatureMap[j].bias);

            for(k=0; k<m_Layer[i].pLayerPrev->m_nFeatureMap; k++)
                for(m=0; m < m_Layer[i].m_KernelSize * m_Layer[i].m_KernelSize; m++)    
                    fscanf(f, "%lg ", &m_Layer[i].m_FeatureMap[j].kernel[k][m]);
        }
    }
    fclose(f);
}

//////////////////////////////////////////////
void CCNN::SaveWeights(char *FileName)
/////////////////////////////////////////////
{
    int i, j, k, m;

    FILE *f;
    if((f = fopen(FileName, "w")) == NULL) return;

    for ( i=1; i<m_nLayer; i++ )
    {
        for( j=0; j<m_Layer[i].m_nFeatureMap; j++ )
        {
            fprintf(f, "%lg ", m_Layer[i].m_FeatureMap[j].bias);

            for(k=0; k<m_Layer[i].pLayerPrev->m_nFeatureMap; k++)
                for(m=0; m < m_Layer[i].m_KernelSize * m_Layer[i].m_KernelSize; m++)    
                {
                    fprintf(f, "%lg ", m_Layer[i].m_FeatureMap[j].kernel[k][m]);
                }
        }
    }

    fclose(f);

}

//////////////////////////////////////////////////////////////////////////
int CCNN::Calculate(double *input, double *output)
//////////////////////////////////////////////////////////////////////////
{
    int i, j;

    //copy input to layer 0
    for(i=0; i<m_Layer[0].m_nFeatureMap; i++)
        for(j=0; j < m_Layer[0].m_FeatureSize * m_Layer[0].m_FeatureSize; j++)
                            m_Layer[0].m_FeatureMap[0].value[j] = input[j];

    //forward propagation 
    //calculate values of neurons in each layer 
    for(i=1; i<m_nLayer; i++)
    {
        //initialization of feature maps to ZERO
        for(j=0; j<m_Layer[i].m_nFeatureMap; j++)
                    m_Layer[i].m_FeatureMap[j].Clear();

        //forward propagation from layer[i-1] to layer[i]
        m_Layer[i].Calculate();
    }

    //copy last layer values to output
    for(i=0; i<m_Layer[m_nLayer-1].m_nFeatureMap; i++) 
        output[i] = m_Layer[m_nLayer-1].m_FeatureMap[i].value[0];

    ///================================
    /*FILE *f; 
    char fileName[100];

    for(i=0; i<m_nLayer; i++) 
    {
        sprintf(fileName, "layer0%d.txt", i);
        f = fopen(fileName, "w");

        for(j=0; j<m_Layer[i].m_nFeatureMap; j++)
        {
            for(k=0; k<m_Layer[i].m_FeatureSize * m_Layer[i].m_FeatureSize; k++)
            {
                if(k%m_Layer[i].m_FeatureSize == 0) fprintf(f, "\n");
                fprintf(f, "%10.7lg\t", m_Layer[i].m_FeatureMap[j].value[k]);
            }           
            fprintf(f, "\n\n\n");
        }
        fclose(f);  
    }*/
    ///==================================

    //get index of highest scoring output feature
    j = 0;
    for(i=1; i<m_Layer[m_nLayer-1].m_nFeatureMap; i++)
        if(output[i] > output[j]) j = i;

    return j;
}

///////////////////////////////////////////////////////////
void CCNN::BackPropagate(double *desiredOutput, double eta)
///////////////////////////////////////////////////////////
{
    int i ;

    //derivative of the error in last layer
    //calculated as difference between actual and desired output (eq. 2)
    for(i=0; i<m_Layer[m_nLayer-1].m_nFeatureMap; i++)
    {
        m_Layer[m_nLayer-1].m_FeatureMap[i].dError[0] = 
            m_Layer[m_nLayer-1].m_FeatureMap[i].value[0] - desiredOutput[i];
    }

    double mse=0.0;
    for ( i=0; i<10; i++ )
    {
            mse += m_Layer[m_nLayer-1].m_FeatureMap[i].dError[0] * m_Layer[m_nLayer-1].m_FeatureMap[i].dError[0];
    }

    //backpropagate through rest of the layers
    for(i=m_nLayer-1; i>0; i--)
    {
        m_Layer[i].BackPropagate(1, eta);
    }

    ///================================ 
    //for debugging: write dError for each feature map in each layer to a file
/*
    FILE *f; 
    char fileName[100];

    for(i=0; i<m_nLayer; i++) 
    {
        sprintf(fileName, "backlx0%d.txt", i);
        f = fopen(fileName, "w");

        for(j=0; j<m_Layer[i].m_nFeatureMap; j++)
        {
            for(k=0; k<m_Layer[i].m_FeatureSize * m_Layer[i].m_FeatureSize; k++)
            {
                if(k%m_Layer[i].m_FeatureSize == 0) fprintf(f, "\n");
                fprintf(f, "%10.7lg\n", m_Layer[i].m_FeatureMap[j].dError[k]);
            }           
            fprintf(f, "\n\n\n");
        }
        fclose(f);  
    }

    //---------------------------------
    //for debugging: write dErr_wrtw for each feature map in each layer to a file

    for(i=1; i<m_nLayer; i++) 
    {
        sprintf(fileName, "backlw0%d.txt", i);
        f = fopen(fileName, "w");

        for(j=0; j<m_Layer[i].m_nFeatureMap; j++)
        {
            fprintf(f, "%10.7lg\n", m_Layer[i].m_FeatureMap[j].dErr_wrtb);

            for(k=0; k<m_Layer[i].pLayerPrev->m_nFeatureMap; k++)
            {
                for(int m=0; m < m_Layer[i].m_KernelSize * m_Layer[i].m_KernelSize; m++)
                {
                    fprintf(f, "%10.7lg\n", m_Layer[i].m_FeatureMap[j].dErr_wrtw[k][m]);
                }
                fprintf(f, "\n\n\n");
            }
        }
        fclose(f);  
    }
    ///==================================
*/
    int t=0;

}

////////////////////////////////////////////////
void CCNN::CalculateHessian( )
////////////////////////////////////////////////
{
    int i, j, k ;

    //2nd derivative of the error wrt Xn in last layer
    //it is always 1
    //Xn is the output after applying SIGMOID

    for(i=0; i<m_Layer[m_nLayer-1].m_nFeatureMap; i++)
    {
        m_Layer[m_nLayer-1].m_FeatureMap[i].dError[0] = 1.0;
    }

    //backpropagate through rest of the layers
    for(i=m_nLayer-1; i>0; i--)
    {
        m_Layer[i].BackPropagate(2, 0);
    }

    //average over the number of samples used
    for(i=1; i<m_nLayer; i++) 
    {
        for(j=0; j<m_Layer[i].m_nFeatureMap; j++)
        {
            m_Layer[i].m_FeatureMap[j].diagHessianBias /= g_cCountHessianSample;

            for(k=0; k<m_Layer[i].pLayerPrev->m_nFeatureMap; k++)
            {
                for(int m=0; m < m_Layer[i].m_KernelSize * m_Layer[i].m_KernelSize; m++)
                {
                    m_Layer[i].m_FeatureMap[j].diagHessian[k][m] /= g_cCountHessianSample;
                }
            }
        }   
    }

    ////-------------------------------
    //saving to files for debugging
    /*FILE *f; 
    char fileName[100];

    for(i=1; i<m_nLayer; i++) 
    {
        sprintf(fileName, "hessian0%d.txt", i);
        f = fopen(fileName, "w");

        for(j=0; j<m_Layer[i].m_nFeatureMap; j++)
        {
            fprintf(f, "%10.7lg\n", m_Layer[i].m_FeatureMap[j].diagHessianBias);
            for(k=0; k<m_Layer[i].pLayerPrev->m_nFeatureMap; k++)
            {
                for(int m=0; m < m_Layer[i].m_KernelSize * m_Layer[i].m_KernelSize; m++)
                {
                    fprintf(f, "%10.7lg\n", m_Layer[i].m_FeatureMap[j].diagHessian[k][m]);
                }
                fprintf(f, "\n\n\n");
            }
        }
        fclose(f);  
    }*/
    ///---------------------------------------

    int t=0;
}


/////////////////////////////////////////////////////////////////////////////////////////////////////
void Layer::Construct(int type, int nFeatureMap, int FeatureSize, int KernelSize, int SamplingFactor)
/////////////////////////////////////////////////////////////////////////////////////////////////////
{
    m_type = type;
    m_nFeatureMap = nFeatureMap;
    m_FeatureSize = FeatureSize;
    m_KernelSize = KernelSize;
    m_SamplingFactor = SamplingFactor;

    m_FeatureMap = new FeatureMap[ m_nFeatureMap ];

    for(int j=0; j<m_nFeatureMap; j++) 
    {
        m_FeatureMap[j].pLayer = this;
        m_FeatureMap[j].Construct(  );
    }
}

/////////////////////////
void Layer::Delete()
/////////////////////////
{
    for(int j=0; j<m_nFeatureMap; j++) m_FeatureMap[j].Delete();
}

///////////////////////////////////////////////////
void Layer::Calculate()     //forward propagation
///////////////////////////////////////////////////
{
    for(int i=0; i<m_nFeatureMap; i++)
    {
        //initialize feature map to bias
        for(int k=0; k < m_FeatureSize * m_FeatureSize; k++)
        {
                m_FeatureMap[i].value[k] = m_FeatureMap[i].bias;
        }

        //calculate effect of each feature map in previous layer
        //on this feature map in this layer
        for(int j=0; j<pLayerPrev->m_nFeatureMap; j++)
        {
            m_FeatureMap[i].Calculate(
                            pLayerPrev->m_FeatureMap[j].value,      //input feature map
                            j                                       //index of input feature map
                                        );
        }

        //SIGMOD function
        for(int j=0; j < m_FeatureSize * m_FeatureSize; j++)
        {
            m_FeatureMap[i].value[j] = 1.7159 * tanh(0.66666667 * m_FeatureMap[i].value[j]);
        }

        //print(i); //for debugging
    }
}


///////////////////////////////////////////////////////////////
void Layer::BackPropagate(int dOrder, double etaLearningRate)       
//////////////////////////////////////////////////////////////
{
    //find dError (2nd derivative) wrt the actual output Yn of this layer
    //Note that SIGMOID was applied to Yn to get Xn during forward propagation
    //We already have dErr_wrt_dXn calculated in CCNN :: BackPropagate and 
    //use the following equation to get dErr_wrt_dYn 
    //dErr_wrt_dYn = InverseSIGMOID(Xn)^2 * dErr_wrt_dXn
    for(int i=0; i<m_nFeatureMap; i++)
    {
        for(int j=0; j < m_FeatureSize * m_FeatureSize; j++)
        {
            double temp = DSIGMOID(m_FeatureMap[i].value[j]);
            if(dOrder == 2) temp *= temp;
            m_FeatureMap[i].dError[j] = temp * m_FeatureMap[i].dError[j];
        }
    }

    //clear dError wrt weights  
    for(int i=0; i<m_nFeatureMap; i++)m_FeatureMap[i].ClearDErrWRTW();

    //clear dError wrt Xn in previous layer.
    //This is input to the previous layer for backpropagation   
    for(int i=0; i<pLayerPrev->m_nFeatureMap; i++)
                        pLayerPrev->m_FeatureMap[i].ClearDError();

    //Backpropagate
    for(int i=0; i<m_nFeatureMap; i++)
    {
        //derivative of error wrt bias
        for(int j=0; j<m_FeatureSize * m_FeatureSize; j++)
            m_FeatureMap[i].dErr_wrtb += m_FeatureMap[i].dError[j];

        //calculate effect of this feature map on each feature map in the revious layer
        for(int j=0; j<pLayerPrev->m_nFeatureMap; j++)
        {
            m_FeatureMap[i].BackPropagate(
                            pLayerPrev->m_FeatureMap[j].value,      //input feature map
                            j,                                      //index of input feature map
                            pLayerPrev->m_FeatureMap[j].dError,     //dErr_wrt_Xn for previous layer
                            dOrder                                  //order of derivative
                                        );
        }
    }

    //update weights (for backporpagation) or diagonal hessian (for 2nd order backpropagation)

    double epsilon, divisor;

    for(int i=0; i<m_nFeatureMap; i++)
    {
        if(dOrder == 1)
        {
            divisor = max(0, m_FeatureMap[i].diagHessianBias) + dMicronLimitParameter;
            epsilon = etaLearningRate / divisor;
            m_FeatureMap[i].bias -= epsilon * m_FeatureMap[i].dErr_wrtb;
        }
        else
        {
            m_FeatureMap[i].diagHessianBias += m_FeatureMap[i].dErr_wrtb;
        }

        for(int j=0; j<pLayerPrev->m_nFeatureMap; j++)
        {
            for(int k=0; k < m_KernelSize * m_KernelSize; k++)
            {
                if(dOrder == 1)
                {
                    divisor = max(0, m_FeatureMap[i].kernel[j][k]) + dMicronLimitParameter;
                    epsilon = etaLearningRate / divisor;
                    m_FeatureMap[i].kernel[j][k] -= epsilon * m_FeatureMap[i].dErr_wrtw[j][k];
                }
                else
                {
                    m_FeatureMap[i].diagHessian[j][k] += m_FeatureMap[i].dErr_wrtw[j][k];
                }
            }
        }
    }

}
















//////////////////////////////////////////////////////////////////////////////////////////
void FeatureMap::Construct( )
//////////////////////////////////////////////////////////////////////////////////////////
{
    if(pLayer->m_type == INPUT_LAYER) m_nFeatureMapPrev = 0;
    else m_nFeatureMapPrev = pLayer->pLayerPrev->m_nFeatureMap;

    int FeatureSize = pLayer->m_FeatureSize;
    int KernelSize  = pLayer->m_KernelSize;

    //neuron values
    value = new double [ FeatureSize * FeatureSize ];

    //error in neuron values
    dError = new double [ FeatureSize * FeatureSize ];

    //weights kernel
    kernel = new double* [ m_nFeatureMapPrev ];
    for(int i=0; i<m_nFeatureMapPrev; i++)
    {
        kernel[i] = new double [KernelSize * KernelSize];

        //initialize
        bias = 0.05 * RANDOM_PLUS_MINUS_ONE;
        for(int j=0; j < KernelSize * KernelSize; j++) kernel[i][j] = 0.05 * RANDOM_PLUS_MINUS_ONE;
    }

    //diagHessian
    diagHessian = new double* [ m_nFeatureMapPrev ];
    for(int i=0; i<m_nFeatureMapPrev; i++) 
        diagHessian[i] = new double [KernelSize * KernelSize];

    //derivative of error wrt kernel weights
    dErr_wrtw = new double* [ m_nFeatureMapPrev ];
    for(int i=0; i<m_nFeatureMapPrev; i++) 
        dErr_wrtw[i] = new double [KernelSize * KernelSize];
}

///////////////////////////
void FeatureMap::Delete()
///////////////////////////
{
    delete[] value;
    delete[] dError;
    for(int i=0; i<m_nFeatureMapPrev; i++) 
    {
        delete[] kernel[i];
        delete[] dErr_wrtw[i];
        delete[] diagHessian[i];
    }
}

////////////////////////////
void FeatureMap::Clear()
/////////////////////////////
{
    for(int i=0; i < pLayer->m_FeatureSize * pLayer->m_FeatureSize; i++) value[i] = 0.0;
}

////////////////////////////////
void FeatureMap::ClearDError()
/////////////////////////////////
{
    for(int i=0; i < pLayer->m_FeatureSize * pLayer->m_FeatureSize; i++) dError[i] = 0.0;
}

///////////////////////////////////
void FeatureMap::ClearDiagHessian()
///////////////////////////////////
{
    diagHessianBias = 0; 
    for(int i=0; i < m_nFeatureMapPrev; i++)
        for(int j=0; j < pLayer->m_KernelSize * pLayer->m_KernelSize; j++) diagHessian[i][j] = 0.0;
}   

////////////////////////////////
void FeatureMap::ClearDErrWRTW()
////////////////////////////////
{
    dErr_wrtb = 0;
    for(int i=0; i < m_nFeatureMapPrev; i++)
        for(int j=0; j < pLayer->m_KernelSize * pLayer->m_KernelSize; j++) dErr_wrtw[i][j] = 0.0;
}

//////////////////////////////////////////////////////////////////////////////////////////////////////
void FeatureMap::Calculate(double *valueFeatureMapPrev, int idxFeatureMapPrev )
//////////////////////////////////////////////////////////////////////////////////////////////////////

//calculate effect of a feature map in previous layer on this feature map in this layer

//  valueFeatureMapPrev:    feature map in previous layer
//  idxFeatureMapPrev :     index of feature map in previous layer

{
    int isize = pLayer->pLayerPrev->m_FeatureSize; //feature size in previous layer
    int ksize = pLayer->m_KernelSize;
    int step_size = pLayer->m_SamplingFactor;       

    int k = 0;

    for(int row0 = 0; row0 <= isize - ksize; row0 += step_size)
        for(int col0 = 0; col0 <= isize - ksize; col0 += step_size)
            value[k++] += Convolute(valueFeatureMapPrev, isize, row0, col0, kernel[idxFeatureMapPrev], ksize);

}



//////////////////////////////////////////////////////////////////////////////////////////////////////
double FeatureMap::Convolute(double *input, int size, int r0, int c0, double *weight, int kernel_size)
//////////////////////////////////////////////////////////////////////////////////////////////////////
{
    int i, j, k = 0;
    double summ = 0;

    for(i = r0; i < r0 + kernel_size; i++)
        for(j = c0; j < c0 + kernel_size; j++)
            summ += input[i * size + j] * weight[k++];

    return summ;
}

/////////////////////////////////////////////////////////////////////////////////////
void FeatureMap::BackPropagate(double *valueFeatureMapPrev, int idxFeatureMapPrev, 
                               double *dErrorFeatureMapPrev, int dOrder )
/////////////////////////////////////////////////////////////////////////////////////

//calculate effect of this feature map on a feature map in previous layer
//note that previous layer is next in backpropagation

//  valueFeatureMapPrev:        feature map in previous layer
//  idxFeatureMapPrev :         index of feature map in previous layer
//  dErrorFeatureMapPrev:       dError wrt neuron values in the FM in prev layer

{
    int isize = pLayer->pLayerPrev->m_FeatureSize;  //size of FM in previous layer
    int ksize = pLayer->m_KernelSize;               //kernel size
    int step_size = pLayer->m_SamplingFactor;       //subsampling factor

    int row0, col0, k;

    k = 0;
    for(row0 = 0; row0 <= isize - ksize; row0 += step_size)
    {
        for(col0 = 0; col0 <= isize - ksize; col0 += step_size)
        {
            for(int i=0; i<ksize; i++)
            {
                for(int j=0; j<ksize; j++)
                {
                    //get dError wrt output for feature map in the previous layer

                    double temp = kernel[idxFeatureMapPrev][i * ksize + j];                 
                    if(dOrder == 1)
                        dErrorFeatureMapPrev[(row0 + i) * isize + (j + col0)] += dError[k] * temp;
                    else
                        dErrorFeatureMapPrev[(row0 + i) * isize + (j + col0)] += dError[k] * temp * temp;

                    //get dError wrt kernel wights

                    temp = valueFeatureMapPrev[(row0 + i) * isize + (j + col0)];
                    if(dOrder == 1)
                        dErr_wrtw[idxFeatureMapPrev][i * ksize + j] += dError[k] * temp;
                    else
                        dErr_wrtw[idxFeatureMapPrev][i * ksize + j] += dError[k] * temp * temp;
                }
            }
            k++;
        }
    }
}

在这项研究中实现显示在上图中。在每一层的特征映射（FM），以及它们的大小的数列的每一个层下。比如第1层有6个特征图，每一个尺寸为13×13的。

内核各特征映射在一个层中含有的数目也示于图中。比如，W [6] [25]依据第2层的书面指示对每一个特征图中该层有6个内核（等于调频的前层中的数量），每一个都具有25的权重（5x5的阵列）。

除了这些权重，每一个FM有一个偏置的重量（它的重要性，请參考不论什么NN文本）。每一个像素具有还有一个參数SF（採样系数）。它会在向前传播部分进行说明。

其它三个參数DBIAS，dErrorW和dErrorFM将在后面章节传播来解释。图中的每一个层以下的最后两行给像素（神经元）和重量。在整个层的总数目。

採用CNN训练的全职保存在一个txt或者xml文件中。

（4）字符识别：对输入的单个字符。採用3.2中预处理，然后输入到3.3中的卷积核，通过BP达到一个结果就是该字符的识别结果。

#include <opencv/highgui.h> 
#include <opencv/cv.h> 

#include "opencv2/core/core.hpp"
#include "opencv2/highgui/highgui.hpp"

#include <iostream>
#include <stdlib.h>
#include <stdio.h>
#include <time.h> /*用到了time函数，所以要有这个头文件*/
#include <fstream>
#include <sstream>
#include <exception>
#include <vector>
#include <io.h>
#include <stdio.h>
#include <math.h>
#include <omp.h>
#include <windows.h>

#include "CNN.h"
#include "global.h"
#include "mnist.h"

using namespace cv;
using namespace std;

int numLine1 = 0; //第一行字符个数
int numLine2 = 0; //第二行字符个数
#define showSteps 1
#define saveImage 1

int an =1;
int element_shape = CV_SHAPE_RECT;
IplConvKernel* element = cvCreateStructuringElementEx( an*2+1, an*2+1, an, an, element_shape, 0 );

LARGE_INTEGER m_liPerfFreq;
LARGE_INTEGER m_liPerfStart;
LARGE_INTEGER liPerfNow;
double dfTim;
void getStartTime()
{
    QueryPerformanceFrequency(&m_liPerfFreq);
    QueryPerformanceCounter(&m_liPerfStart);
}

void getEndTime()
{
    QueryPerformanceCounter(&liPerfNow);
    dfTim=( ((liPerfNow.QuadPart - m_liPerfStart.QuadPart) * 1000.0f)/m_liPerfFreq.QuadPart);
}

//config.txt为要处理的跟文件夹，在训练model中，config.txt中的内容为训练是的样本库，1-13分类好了。

--

//在样本筛选model中。config.txt里的内容为要筛选的样本库，未分类。--- char * configFile = "config.txt"; //读取config文件中的内容-- char* trainSetPosPath = (char *)malloc(200*sizeof(char)); void readConfig(char* configFile, char* trainSetPosPath){ fstream f; char cstring[1000]; int readS=0; f.open(configFile, fstream::in); char param1[200]; strcpy(param1,""); char param2[200]; strcpy(param2,""); char param3[200]; strcpy(param3,""); //--读取第一行：-- f.getline(cstring, sizeof(cstring)); readS=sscanf (cstring, "%s %s %s", param1,param2, param3); strcpy(trainSetPosPath,param3); //--读取第二行：-- 字符个数 f.getline(cstring, sizeof(cstring)); readS=sscanf (cstring, "%s %s %i", param1,param2, &numLine1); //--读取第三行：-- 字符个数 f.getline(cstring, sizeof(cstring)); readS=sscanf (cstring, "%s %s %i", param1,param2, &numLine2); } //遍历config.txt里的根文件夹下的全部的文件，包含子文件夹。-- // 当中子文件夹的名字就是label，子文件夹里的文件为label对于的训练測试样本--- vector<string> imgNames; int labelTemp = 0; void dfsFolder(string folderPath){ _finddata_t FileInfo; string strfind = folderPath + "\\*"; long Handle = _findfirst(strfind.c_str(), &FileInfo); if (Handle == -1L) { cerr << "can not match the folder path" << endl; exit(-1); } do{ //推断是否有子文件夹-- if (FileInfo.attrib & _A_SUBDIR) { // cout<<FileInfo.name<<" "<<FileInfo.attrib<<endl; //这个语句非常重要-- if( (strcmp(FileInfo.name,".") != 0 ) &&(strcmp(FileInfo.name,"..") != 0)) { string newPath = folderPath + "\\" + FileInfo.name; cout<<FileInfo.name<<" "<<newPath<<endl; //根文件夹下下的子文件夹名字就是label名，假设没有子文件夹则其为根文件夹下 labelTemp = atoi(FileInfo.name); // printf("%d\n",labelTemp); dfsFolder(newPath); } }else { string finalName = folderPath + "\\" + FileInfo.name; //将全部的文件名称写入一个txt文件-- // cout << FileInfo.name << "\t"; // printf("%d\t",label); // cout << folderPath << "\\" << FileInfo.name << " " <<endl; //将文件名称字和label名字（子文件夹名字赋值给向量）-- imgNames.push_back(finalName); } }while (_findnext(Handle, &FileInfo) == 0); _findclose(Handle); } void initTrainImage(){ readConfig(configFile, trainSetPosPath); string folderPath = trainSetPosPath; dfsFolder(folderPath); } //CNN识别初始化部分 void init(){ m_bTestSetOpen = m_bTrainingSetOpen = false; m_bStatusTraining = false; m_bStatusTesting = false; m_iCountTotal = 0; m_iCountError = 0; m_dDispX = new double[g_cVectorSize * g_cVectorSize]; m_dDispY = new double[g_cVectorSize * g_cVectorSize]; m_etaLearningRate = 0.00005; } void Calculate(IplImage *img){ Also create a color image (for display) //IplImage *colorimg = cvCreateImage( inputsz, IPL_DEPTH_8U, 3 ); //get image data int index = 0; for(int i = 0; i < img->height; ++i){ for(int j = 0; j < img->width; ++j){ index = i*img->width + j; grayArray[index] = ((uchar*)(img->imageData + i*img->widthStep))[j] ; //为像素赋值 } } int ii, jj; //copy gray scale image to a double input vector in -1 to 1 range // one is white, -one is black for ( ii=0; ii<g_cVectorSize * g_cVectorSize; ++ii ) inputVector[ii] = 1.0; for ( ii=0; ii<g_cImageSize; ++ii ) { for ( jj=0; jj<g_cImageSize; ++jj ) { int idxVector = 1 + jj + g_cVectorSize * (1 + ii); int idxImage = jj + g_cImageSize * ii; inputVector[ idxVector ] = double(255 - grayArray[ idxImage ])/128.0 - 1.0; } } //call forward propagation function of CNN m_iOutput = m_cnn.Calculate(inputVector, outputVector); } uchar lut[256]; CvMat* lut_mat; IplImage * dehist(IplImage * src_image, int _brightness, int _contrast){ IplImage *dst_image = cvCreateImage(cvGetSize(src_image),8,src_image->nChannels); cvCopy(src_image,dst_image); int brightness = _brightness - 100; int contrast = _contrast - 100; int i; float max_value = 0; if( contrast > 0 ) { double delta = 127.*contrast/100; double a = 255./(255. - delta*2); double b = a*(brightness - delta); for( i = 0; i < 256; i++ ) { int v = cvRound(a*i + b); if( v < 0 ) v = 0; if( v > 255 ) v = 255; lut[i] = (uchar)v; } } else { double delta = -128.*contrast/100; double a = (256.-delta*2)/255.; double b = a*brightness + delta; for( i = 0; i < 256; i++ ) { int v = cvRound(a*i + b); if( v < 0 ) v = 0; if( v > 255 ) v = 255; lut[i] = (uchar)v; } } lut_mat = cvCreateMatHeader( 1, 256, CV_8UC1 ); cvSetData( lut_mat, lut, 0 ); cvLUT( src_image, dst_image, lut_mat ); if(showSteps) cvShowImage( "dst_image", dst_image ); IplImage* gray_image = cvCreateImage(cvGetSize(src_image),8,1); cvCvtColor(dst_image, gray_image, CV_BGR2GRAY); IplImage* bin_image = cvCreateImage(cvGetSize(src_image),8,1); // int blockSize = 11; // int constValue = 9; // cvAdaptiveThreshold(gray_image, bin_image, 255, CV_ADAPTIVE_THRESH_MEAN_C, CV_THRESH_BINARY, blockSize, constValue); cvThreshold(gray_image,bin_image,1,255,CV_THRESH_BINARY+CV_THRESH_OTSU); if(showSteps) cvShowImage( "bin_image", bin_image ); // OpenClose(bin_image,bin_image,-1); //cvErode(bin_image,bin_image,element,1); //cvDilate(bin_image,bin_image,element,8); cvReleaseImage(&dst_image); cvReleaseImage(&gray_image); return bin_image; } IplImage * projectY(IplImage * src){ IplImage *imgBin = cvCreateImage(cvGetSize(src),8,src->nChannels); cvCopy(src,imgBin); cvNot(src,imgBin); //Y轴投影 确定字符详细区域 IplImage* painty=cvCreateImage( cvGetSize(imgBin),IPL_DEPTH_8U, 1 ); cvZero(painty); int* h=new int[imgBin->height]; memset(h,0,imgBin->height*4); int x,y; CvScalar s,t; for(y=0;y<imgBin->height;y++) { for(x=0;x<imgBin->width;x++) { s=cvGet2D(imgBin,y,x); if(s.val[0]==0) h[y]++; } } //将y投影后，值小于50的赋值为0 for(y=0;y<imgBin->height;y++) { if((imgBin->width-h[y]) <= 13) h[y] = imgBin->width; // printf("%d ",imgBin->width-h[y]); } //将Y轴上 非常窄的线段，即横着的非常长的细线直接抹掉 for(x=0;x<painty->height;x++) { for(y=x;y<painty->height;y++) { if( (h[x] == h[y])&&(h[y] == painty->width)&&(y-x <= 3) ){ for(int i=x;i<=y;i++){ h[i] = painty->width; } } if( (h[x] != painty->width)&&(h[y] == painty->width)&&(y-x <= 3) ){ for(int i=x;i<=y;i++){ h[i] = painty->width; } } } } for(y=0;y<imgBin->height;y++) { for(x=0;x<h[y];x++) { t.val[0]=255; cvSet2D(painty,y,x,t); } } //确定Y轴字符的收尾。确定字符区域的高度 //查找paintx首尾两端的x轴坐标 int xLeft = 0; for(x=0;x<painty->height-2;x++){ if ( cvGet2D(painty,x,painty->width - 1).val[0]== 0 ){ xLeft = x; break; } if( (cvGet2D(painty,x,painty->width - 1).val[0] == 255)&&(cvGet2D(painty,x+1,painty->width - 1).val[0] == 0) ){ xLeft = x; break; } } if(showSteps) cout<<"列字符区域上边字符起始点是："<<xLeft<<endl; int xRight = 0; for(x=painty->height-1; x>0 ;x--){ if ( cvGet2D(painty,x,painty->width - 1).val[0]== 0 ){ xRight = x; break; } if( (cvGet2D(painty,x,painty->width - 1).val[0]== 255)&&(cvGet2D(painty,x-1,painty->width - 1).val[0] == 0) ){ xRight = x; break; } } if(xRight == 0) xRight = painty->height; if(showSteps) cout<<"列字符区域下边字符起始点是："<<xRight<<endl; if(showSteps){ cvNamedWindow("水平积分投影",1); cvShowImage("水平积分投影",painty); } IplImage * image = cvCreateImage(cvSize((src->width),xRight - xLeft + 4),8,src->nChannels); CvRect rect; rect.height = xRight - xLeft+4 ; rect.width = src->width; rect.x = 0; rect.y = xLeft-2; cvSetImageROI(src,rect); cvCopy(src,image); cvResetImageROI(src); cvReleaseImage(&imgBin); // cvReleaseImage(&src); cvReleaseImage(&painty); cvNamedWindow("image1",1); cvShowImage("image1",image); return image; } IplImage* projectX(IplImage * src){ // cvSmooth(src,src,CV_BLUR,3,3,0,0); IplImage * srcTemp = cvCreateImage(cvGetSize(src),8,src->nChannels); cvCopy(src,srcTemp); cvThreshold(src,src,50,255,CV_THRESH_BINARY_INV+CV_THRESH_OTSU); IplImage* paintx=cvCreateImage(cvGetSize(src),IPL_DEPTH_8U, 1 ); cvZero(paintx); int* v=new int[src->width]; int tempx=src->height; // CvPoint xPoint; int tempy=src->width; memset(v,0,src->width*4); int x,y; CvScalar s,t; for(x=0;x<src->width;x++){ for(y=0;y<src->height;y++){ s=cvGet2D(src,y,x); if(s.val[0]==0) v[x]++; } } //将x投影后，值小于2的赋值为0 for(x=0;x<src->width;x++) { if((src->height-v[x]) <= 3) v[x] = src->height; // printf("%d ",src->height-v[x]); } //若投影后出现非常细的竖直黑线，将这条黑线去掉 for(x=0;x<paintx->width;x++) { for(y=x;y<paintx->width;y++) { if( (v[x] == v[y])&&(v[y] == paintx->height)&&(y-x < 3) ){ for(int i=x;i<=y;i++){ v[i] = paintx->height; } } if( (v[x] != paintx->width)&&(v[y] == paintx->width)&&(y-x <= 3) ){ for(int i=x;i<=y;i++){ v[i] = paintx->height; } } } } for(x=0;x<src->width;x++){ for(y=0;y<v[x];y++){ t.val[0]=255; cvSet2D(paintx,y,x,t); } } //查找paintx首尾两端的x轴坐标 int xLeft = 0; for(x=0;x<paintx->width;x++){ if( (cvGet2D(paintx,paintx->height - 3,x).val[0] == 255)&&(cvGet2D(paintx,paintx->height - 3,x+1).val[0] == 0) ){ xLeft = x; break; } } if(showSteps) cout<<"行字符区域左边字符起始点是："<<xLeft<<endl; int xRight = 0; for(x=paintx->width-1; x>0 ;x--){ if( (cvGet2D(paintx,paintx->height - 1,x).val[0]== 255)&&(cvGet2D(paintx,paintx->height - 1,x-1).val[0] == 0) ){ xRight = x; break; } } if(showSteps) cout<<"行字符区域左边字符起始点是："<<xRight<<endl; if(showSteps){ cvNamedWindow("二值图像",1); cvNamedWindow("垂直积分投影",1); cvShowImage("二值图像",src); cvShowImage("垂直积分投影",paintx); } IplImage * image = cvCreateImage(cvSize((xRight - xLeft),src->height),8,src->nChannels); CvRect rect; rect.height = src->height; rect.width = xRight - xLeft; rect.x = xLeft; rect.y = 0; cvSetImageROI(srcTemp,rect); cvCopy(srcTemp,image); cvResetImageROI(srcTemp); cvReleaseImage(&src); cvReleaseImage(&srcTemp); cvReleaseImage(&paintx); //cvNamedWindow("image",1); //cvShowImage("image",image); //cvWaitKey(0); return image; } char recVifcode(IplImage *src){ // Grayscale img pointer if (!src){ cout << "ERROR: Bad image file: " << endl; // continue; } CvSize inputsz = cvSize(28,28); // Grayscale img pointer IplImage* img = cvCreateImage( inputsz, IPL_DEPTH_8U, 1 ); // create some GUI if(showSteps){ cvNamedWindow("Image", CV_WINDOW_AUTOSIZE); cvMoveWindow("Image", inputsz.height, inputsz.width); } cvResize(src,img,CV_INTER_CUBIC); Calculate(img); if(showSteps){ cvShowImage("Image",img); } /*IplImage* imgDistorted = cvCreateImage( inputsz, IPL_DEPTH_8U, 1 ); cvCopy(img,imgDistorted); for(int i = 0; i < imgDistorted->height; ++i){ for(int j = 0; j < imgDistorted->width; ++j){ ((uchar*)(imgDistorted->imageData + i*imgDistorted->widthStep))[j] = (unsigned char) int (255 - 255 * (inputVector[(i+1)*g_cVectorSize + j + 1] + 1)/2); } } if(showSteps){ cvNamedWindow("imgDistorted", CV_WINDOW_AUTOSIZE); cvShowImage("imgDistorted",imgDistorted); }*/ // cout<<"识别结果为："<<m_iOutput<<endl; char outputChar = NULL; if(m_iOutput == 0) outputChar = '0'; if(m_iOutput == 1) outputChar = '1'; if(m_iOutput == 2) outputChar = '2'; if(m_iOutput == 3) outputChar = '3'; if(m_iOutput == 4) outputChar = '4'; if(m_iOutput == 5) outputChar = '5'; if(m_iOutput == 6) outputChar = '6'; if(m_iOutput == 7) outputChar = '7'; if(m_iOutput == 8) outputChar = '8'; if(m_iOutput == 9) outputChar = '9'; if(m_iOutput == 10) outputChar = 'A'; if(m_iOutput == 11) outputChar = 'B'; if(m_iOutput == 12) outputChar = 'U'; if(m_iOutput == 13) outputChar = 'D'; if(m_iOutput == 14) outputChar = 'P'; if(m_iOutput == 15) outputChar = 'R'; if(m_iOutput == 16) outputChar = 'S'; if(m_iOutput == 17) outputChar = 'T'; if(m_iOutput == 18) outputChar = 'U'; if(m_iOutput == 19) outputChar = 'X'; if(m_iOutput == 20) outputChar = 'Y'; // cout<<"识别结果为："<<outputChar<<endl; return outputChar; } void saveImages(IplImage * image){ SYSTEMTIME stTime; GetLocalTime(&stTime); char pVideoName[256]; sprintf(pVideoName, ".\\%d_%d_%d_%d_%d_%d_%d", stTime.wYear, stTime.wMonth, stTime.wDay, stTime.wHour, stTime.wMinute, stTime.wSecond, stTime.wMilliseconds); char image_name[500] ; sprintf_s(image_name,500, "%s%s%s", "result\\", pVideoName, ".bmp");//保存的图片名 cvSaveImage(image_name, image); } vector<char> segChar(IplImage * src,int x){ vector<char>imageRecLine1; //保存第一行的识别结果 vector<char>imageRecLine2;//保存第二行的识别结果 if((x!=1)&&(x!=2)){ printf("error! 必须指定是第几行！"); // return NULL; } // cvErode(src,src,element,1); if(showSteps) cvShowImage( "src", src ); //想垂直方向投影，确定字符区域的首尾，用于切割出单个字符 IplImage * image = projectX(src); if(x == 1){//第一行 //================推断第一个字符是否为 1 ===========================/ CvRect rectFirst; rectFirst.height = image->height; rectFirst.width = image->width/numLine1; rectFirst.x = 0; rectFirst.y = 0; IplImage * imageRoiFirst = cvCreateImage(cvSize(rectFirst.width,rectFirst.height),8,image->nChannels); cvSetImageROI(image,rectFirst); cvCopy(image,imageRoiFirst); cvResetImageROI(image); if(saveImage) saveImages(imageRoiFirst); char recResultFirst = recVifcode(imageRoiFirst); if(recResultFirst == '1'){ /*cout<<"wwwwwwwwwwwwwwwwwwwwwwwww"<<endl;*/ imageRecLine2.push_back(recResultFirst);//保存第二行的第一个字符1的识别结果 const int firstLen = 20; for(int i=0;i<numLine1-1;i++){ CvRect rect; rect.height = image->height; rect.width = (image->width-firstLen)/(numLine1-1); rect.x = i*(image->width-firstLen)/(numLine1-1) + firstLen; rect.y = 0; IplImage * imageRoi = cvCreateImage(cvSize(rect.width,rect.height),8,image->nChannels); cvSetImageROI(image,rect); cvCopy(image,imageRoi); cvResetImageROI(image); cvShowImage("1",imageRoi); cvWaitKey(0); if(saveImage) saveImages(imageRoi); //调用识别部分代码 char recResult = recVifcode(imageRoi); imageRecLine2.push_back(recResult);//保存第二行的识别结果 } }else{ for(int i=0;i<numLine1;i++){ CvRect rect; rect.height = image->height; rect.width = image->width/numLine1; rect.x = i*image->width/numLine1; rect.y = 0; IplImage * imageRoi = cvCreateImage(cvSize(rect.width,rect.height),8,image->nChannels); cvSetImageROI(image,rect); cvCopy(image,imageRoi); cvResetImageROI(image); cvShowImage("1",imageRoi); cvWaitKey(0); if(saveImage) saveImages(imageRoi); //调用识别部分代码 char recResult = recVifcode(imageRoi); imageRecLine1.push_back(recResult);//保存第二行的识别结果 } } return imageRecLine1; } if(x == 2){//第一行 //================推断第一个字符是否为 1 ===========================/ CvRect rectFirst; rectFirst.height = image->height; rectFirst.width = image->width/numLine2; rectFirst.x = 0; rectFirst.y = 0; IplImage * imageRoiFirst = cvCreateImage(cvSize(rectFirst.width,rectFirst.height),8,image->nChannels); cvSetImageROI(image,rectFirst); cvCopy(image,imageRoiFirst); cvResetImageROI(image); if(saveImage) saveImages(imageRoiFirst); char recResultFirst = recVifcode(imageRoiFirst); if(recResultFirst == '1'){ /*cout<<"wwwwwwwwwwwwwwwwwwwwwwwww"<<endl;*/ imageRecLine2.push_back(recResultFirst);//保存第二行的第一个字符1的识别结果 const int firstLen = 20; for(int i=0;i<numLine2-1;i++){ CvRect rect; rect.height = image->height; rect.width = (image->width-firstLen)/(numLine2-1); rect.x = i*(image->width-firstLen)/(numLine2-1) + firstLen; rect.y = 0; IplImage * imageRoi = cvCreateImage(cvSize(rect.width,rect.height),8,image->nChannels); cvSetImageROI(image,rect); cvCopy(image,imageRoi); cvResetImageROI(image); cvShowImage("1",imageRoi); cvWaitKey(0); if(saveImage) saveImages(imageRoi); //调用识别部分代码 char recResult = recVifcode(imageRoi); imageRecLine2.push_back(recResult);//保存第二行的识别结果 } }else{ for(int i=0;i<numLine2;i++){ CvRect rect; rect.height = image->height; rect.width = image->width/numLine2; rect.x = i*image->width/numLine2; rect.y = 0; IplImage * imageRoi = cvCreateImage(cvSize(rect.width,rect.height),8,image->nChannels); cvSetImageROI(image,rect); cvCopy(image,imageRoi); cvResetImageROI(image); cvShowImage("1",imageRoi); cvWaitKey(0); if(saveImage) saveImages(imageRoi); //调用识别部分代码 char recResult = recVifcode(imageRoi); imageRecLine2.push_back(recResult);//保存第二行的识别结果 } } return imageRecLine2; } } void printResult(vector<char> imageRecLine){ int recNum = imageRecLine.size(); for(int iNum=0;iNum<recNum;iNum++){ cout<<imageRecLine[iNum]; } cout<<endl; } void processingTotal(){ initTrainImage(); char * weightFileName = "Weight.txt"; m_cnn.LoadWeights(weightFileName); int imgNum = imgNames.size(); for(int iNum=0;iNum<imgNum;iNum++){ cout<<endl<<iNum<<endl; cout<<imgNames[iNum].c_str()<<endl; IplImage * src=cvLoadImage(imgNames[iNum].c_str(),1); if(!src) continue; // // // Mat image(src); // Mat dst = image.clone(); for ( int i = 1; i < 480; i = i + 2 ){ // int i = 30; // bilateralFilter ( image, dst, i, i*2, i/2 ); // imshow( "image", image ); // imshow( "dst", dst ); // waitKey ( 0 ); } // /// getStartTime(); IplImage * tgray = cvCreateImage(cvGetSize(src),8,1); cvCvtColor(src,tgray,CV_BGR2GRAY); IplImage * bin_image = cvCreateImage(cvGetSize(src),8,1); bin_image = dehist(src,83,134); cvErode(bin_image,bin_image,element,12); if(showSteps) cvShowImage( "bin_image1", bin_image ); CvMemStorage *mems=cvCreateMemStorage(); CvSeq *contours; cvFindContours( bin_image, mems, &contours,sizeof(CvContour),CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE); // cvDrawContours(src, contours, CV_RGB(0,0,255), CV_RGB(255, 0, 0), 2, 2, 8, cvPoint(0,0)); cvClearMemStorage( mems ); if(showSteps){ cvNamedWindow("cvDrawContours",1); cvShowImage("cvDrawContours",src); } CvRect rect; // char image_name[100]; CvSeq* first_seq = contours; // int image_num = 0; for( contours=first_seq; contours != 0; contours = contours->h_next ){ rect = cvBoundingRect(contours); cout<<rect.x<<" "<<rect.y<<" "<<rect.width<<" "<<rect.height<<endl; //依据轮廓大小信息做筛选 if( (rect.width > 440)||(rect.height > 300)|| // (rect.width/rect.height > 5)|| (rect.width*rect.height < 4500)|| (rect.width < 100)||(rect.height < 50)|| (rect.x < 0)||(rect.y < 0)|| (rect.x > src->width)||(rect.y > src->height) ) continue; else{ CvPoint pt1;pt1.x = rect.x; pt1.y = rect.y; CvPoint pt2;pt2.x = rect.x + rect.width; pt2.y = rect.y + rect.height; if(showSteps){ cvRectangle(src,pt1,pt2,CV_RGB(255,0,255),2/*CV_FILLED*/,CV_AA,0); cout<<rect.x<<" "<<rect.y<<" "<<rect.width<<" "<<rect.height<<endl; } if(showSteps){ cvNamedWindow("cvDrawContours",1); cvShowImage("cvDrawContours",src); } //扣出字符区域后，在对小图的字符区域做二值化，滤波，然后roi，旋转矫正？？？？？？？？？？ CvRect rectTemple; rectTemple.x = rect.x - 5; rectTemple.y = rect.y - 5; rectTemple.width = rect.width + 10; rectTemple.height = rect.height + 10; IplImage* tempImage = cvCreateImage(cvSize(rectTemple.width,rectTemple.height),8,1); cvSetImageROI(tgray,rectTemple); cvCopy(tgray,tempImage); cvResetImageROI(tgray); cvThreshold(tempImage,tempImage,1,255,CV_THRESH_BINARY+CV_THRESH_OTSU); if(showSteps){ cvNamedWindow("tempImage",1); cvShowImage("tempImage",tempImage); } CvBox2D box_outer = cvMinAreaRect2(contours); // cout<<box_outer.center.x<<" "<<box_outer.center.y<<" "<<box_outer.angle<<" "<<box_outer.size.width<<" "<<box_outer.size.height<<endl; //旋转矫正tempImage IplImage* tempImageRotate = cvCreateImage(cvGetSize(tempImage),8,1); float m[6]; // Matrix m looks like: // // [ m0 m1 m2 ] ===> [ A11 A12 b1 ] // [ m3 m4 m5 ] [ A21 A22 b2 ] // CvMat M = cvMat (2, 3, CV_32F, m); int w = tempImage->width; int h = tempImage->height; if( (box_outer.angle+90.)<45 ){ // 只旋转 int factor = 1; m[0] = (float) (factor * cos ((-1)*(box_outer.angle+90.)/2. * 2 * CV_PI / 180.)); m[1] = (float) (factor * sin ((-1)*(box_outer.angle+90.)/2. * 2 * CV_PI / 180.)); m[3] = (-1)*m[1]; m[4] = m[0]; // 将旋转中心移至图像中间 m[2] = w * 0.5f; m[5] = h * 0.5f; // dst(x,y) = A * src(x,y) + b } if( (box_outer.angle+90.)>45 ){ // 只旋转 int factor = 1; m[0] = (float) (factor * cos ((-1)*(box_outer.angle)/2. * 2 * CV_PI / 180.)); m[1] = (float) (factor * sin ((-1)*(box_outer.angle)/2. * 2 * CV_PI / 180.)); m[3] = (-1)*m[1]; m[4] = m[0]; // 将旋转中心移至图像中间 m[2] = w * 0.5f; m[5] = h * 0.5f; // dst(x,y) = A * src(x,y) + b } cvZero (tempImageRotate); cvGetQuadrangleSubPix (tempImage, tempImageRotate, &M); if(showSteps){ cvNamedWindow("ROI",1); cvShowImage("ROI",tempImageRotate); } cvReleaseImage( &tempImage ); //====================对tempImageRotate做Y轴投影===================// IplImage* imageCharOk = projectY(tempImageRotate); //直接上下 均分 切割出上下两行 CvRect rectTop; rectTop.x = 0; rectTop.y = 0; rectTop.width = imageCharOk->width ; rectTop.height = imageCharOk->height/2; IplImage* imageCharOkTop = cvCreateImage(cvSize(rectTop.width,rectTop.height),8,1); cvSetImageROI(imageCharOk,rectTop); cvCopy(imageCharOk,imageCharOkTop); cvResetImageROI(imageCharOk); if(showSteps){ cvNamedWindow("imageCharOkTop",1); cvShowImage("imageCharOkTop",imageCharOkTop); } vector<char> results = segChar(imageCharOkTop,1); printResult(results); CvRect rectBottom; rectBottom.x = 0; rectBottom.y = 0 + imageCharOk->height/2; rectBottom.width = imageCharOk->width ; rectBottom.height = imageCharOk->height/2; IplImage* imageCharOkBottom = cvCreateImage(cvSize(rectBottom.width,rectBottom.height),8,1); cvSetImageROI(imageCharOk,rectBottom); cvCopy(imageCharOk,imageCharOkBottom); cvResetImageROI(imageCharOk); if(showSteps){ cvNamedWindow("imageCharOkBottom",1); cvShowImage("imageCharOkBottom",imageCharOkBottom); } vector<char> results2 = segChar(imageCharOkBottom,2); printResult(results2); } } getEndTime(); printf("%f 毫秒\n",dfTim); cvWaitKey(0); cvReleaseImage( &src ); cvReleaseImage( &tgray ); cvReleaseImage( &bin_image ); } } void main(){ init(); processingTotal(); }