文檔圖像傾斜校正算法(1)——文本行投影法

文檔圖像傾斜校正算法(1)——文本行投影法

原理：沿着文本行的方向對文本行進行投影得到的投影值集合，要比其他方向投影值集合的方差要大。

適用範圍：投影求方差的方法適用於圖像局部變形較小，干擾少的文檔圖像。在實現時可以先在圖像中扣取一塊文本行清晰的圖像，再在扣取的小圖上採用該方法進行圖像傾斜校正。

下面代碼是在做火車票識別時的傾斜校正程序，利用二維碼檢測的位置框取一部分文檔圖像，再使用該部分文檔圖像完成傾斜校正（只放了傾斜校正的代碼）：

#include <opencv2/opencv.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <vector>
#include <numeric>
#define MY_SKEW 14

//圖像旋轉1：旋轉（截取圖像）Crop
//         Mat img ：圖像輸入，單通道或者三通道
//         Mat & imgout ：圖像輸出
//         int degree ：圖像要旋轉的角度
//         int border_value：圖像旋轉填充值
int rotateImage1(Mat img,Mat & imgout, int degree,int border_value)
{
    if( img.empty())
        return 1;
    degree = -degree;//warpAffine默認的旋轉方向是逆時針，所以加負號表示轉化爲順時針
    double angle = degree  * CV_PI / 180.; // 弧度  
    double a = sin(angle), b = cos(angle);
    int width = img.cols;
    int height = img.rows;
    int width_rotate = int(width * fabs(b)-height * fabs(a));//height * fabs(a) +
    int height_rotate = int(height * fabs(b)-width * fabs(a));//width * fabs(a) +
    if(width_rotate<=20||height_rotate<=20)
    {
        width_rotate = 20;
        height_rotate = 20;
    }
    //旋轉數組map
    // [ m0  m1  m2 ] ===>  [ A11  A12   b1 ]
    // [ m3  m4  m5 ] ===>  [ A21  A22   b2 ]
    float map[6];
    Mat map_matrix = Mat(2, 3, CV_32F, map);
    // 旋轉中心
    CvPoint2D32f center = cvPoint2D32f(width / 2, height / 2);
    CvMat map_matrix2 = map_matrix;
    cv2DRotationMatrix(center, degree, 1.0, &map_matrix2);//計算二維旋轉的仿射變換矩陣
    map[2] += (width_rotate - width) / 2;
    map[5] += (height_rotate - height) / 2;
    //Mat img_rotate;
    //對圖像做仿射變換
    //CV_WARP_FILL_OUTLIERS - 填充所有輸出圖像的象素。
    //如果部分象素落在輸入圖像的邊界外，那麼它們的值設定爲 fillval.
    //CV_WARP_INVERSE_MAP - 指定 map_matrix 是輸出圖像到輸入圖像的反變換，
    int chnnel =img.channels();
    if(chnnel == 3)
        warpAffine(img, imgout, map_matrix, Size(width_rotate, height_rotate), 1, 0, Scalar(border_value,border_value,border_value));
    else
        warpAffine(img, imgout, map_matrix, Size(width_rotate, height_rotate), 1, 0, border_value);
    return 0;
}

//圖像旋轉2：擴充圖像邊緣full
//         Mat img ：圖像輸入，單通道或者三通道
//         Mat & imgout ：圖像輸出
//         int degree ：圖像要旋轉的角度
//         int border_value：圖像旋轉填充值
int rotateImage2(Mat img,Mat & imgout, int degree,int border_value)
{
    if(img.empty())
        return 1;
    degree = -degree;//warpAffine默認的旋轉方向是逆時針，所以加負號表示轉化爲順時針
    double angle = degree  * CV_PI / 180.; // 弧度  
    double a = sin(angle), b = cos(angle);
    int width = img.cols;
    int height = img.rows;
    int width_rotate = int(width * fabs(b)+height * fabs(a));//height * fabs(a) +
    int height_rotate = int(height * fabs(b)+width * fabs(a));//width * fabs(a) +
    if(width_rotate<=20||height_rotate<=20)
    {
        width_rotate = 20;
        height_rotate = 20;
    }
    //旋轉數組map
    // [ m0  m1  m2 ] ===>  [ A11  A12   b1 ]
    // [ m3  m4  m5 ] ===>  [ A21  A22   b2 ]
    float map[6];
    Mat map_matrix = Mat(2, 3, CV_32F, map);
    // 旋轉中心
    CvPoint2D32f center = cvPoint2D32f(width / 2, height / 2);
    CvMat map_matrix2 = map_matrix;
    cv2DRotationMatrix(center, degree, 1.0, &map_matrix2);//計算二維旋轉的仿射變換矩陣
    map[2] += (width_rotate - width) / 2;
    map[5] += (height_rotate - height) / 2;
    //Mat img_rotate;
    //對圖像做仿射變換
    //CV_WARP_FILL_OUTLIERS - 填充所有輸出圖像的象素。
    //如果部分象素落在輸入圖像的邊界外，那麼它們的值設定爲 fillval.
    //CV_WARP_INVERSE_MAP - 指定 map_matrix 是輸出圖像到輸入圖像的反變換，
    Mat imgout_pro;
    int chnnel =img.channels();
    if(chnnel == 3)
        warpAffine(img, imgout_pro, map_matrix, Size(width_rotate, height_rotate), 1, 0, Scalar(border_value, border_value, border_value));
    else
        warpAffine(img, imgout_pro, map_matrix, Size(width_rotate, height_rotate), 1, 0, border_value);

    resize(imgout_pro, imgout, Size(imgout_pro.rows, imgout_pro.cols), 0, 0, 1);
    return 0;
}

//投影傾斜校正：火車票傾斜矯正方法舉例
//         const Mat imgin ：圖像輸入，三通道
//         Mat & imgout ：矯正後的圖像輸出
//         int &theta ：圖像傾斜的角度
int skew_correction_projector(const Mat imgin, Mat & imgout, int &theta)
{
    if (imgin.empty())
    {
        return 1;
    }
    if (imgin.channels() != 3)
    {
        return 1;
    }
    Mat Gray;
    cvtColor(imgin, Gray, COLOR_RGB2GRAY);
    medianBlur(Gray, Gray, 3);
    //imwrite(imagename_out3, code_cropout_resize);

    float zoom_ratio = 800.0 / imgin.rows;
    resize(Gray, Gray, Size(0, 0), zoom_ratio, zoom_ratio, 1);
    Mat Bin;
    adaptiveThreshold(Gray, Bin, 255, CV_ADAPTIVE_THRESH_GAUSSIAN_C, CV_THRESH_BINARY, 201, 5.0);
    Mat bincut = Bin.clone()
    Mat img_skew;
    unsigned int matrik2[2 * MY_SKEW + 1];
    for (int skew = -MY_SKEW; skew <= MY_SKEW; skew++)
    {
        rotateImage2(bincut, img_skew, skew, 255);
        threshold(img_skew, img_skew, 180, 255, THRESH_BINARY);
        Mat img_skew0 = 255 - img_skew;
        vector<unsigned int> rows_pro;
        unsigned int rows_project;

        for (int i = 0; i<img_skew.rows; i++)
        {
            rows_project = 0;
            for (int j = 0; j<img_skew.cols; j++)
            {
                if (img_skew.at<uchar>(i, j)>0)
                    rows_project++;
            }
            rows_pro.push_back(rows_project);
        }


        double sum = std::accumulate(std::begin(rows_pro), std::end(rows_pro), 0.0);
        double mean = sum / rows_pro.size(); //均值

        double accum = 0.0;
        std::for_each(std::begin(rows_pro), std::end(rows_pro), [&](const double d) {
            accum += (d - mean)*(d - mean);
        });

        double stdev = sqrt(accum / (rows_pro.size() - 1)); //方差

        matrik2[skew + MY_SKEW] = stdev;
    }
    theta = (int)distance(matrik2, max_element(matrik2, matrik2 + sizeof(matrik2) / sizeof(matrik2[0]))) - MY_SKEW;
    rotateImage1(imgin, imgout, theta, 0);
    return 0;
}