使用 opencv 和 c++ 获取书籍图像

Posted 2023-02-21

【中文标题】使用 opencv 和 c++ 获取书籍图像

【英文标题】：Getting a book image using opencv and c++

【发布时间】：2017-08-03 18:46:39

【问题描述】：

我正在尝试使用findcontours 检测以下书籍，但根本无法检测到它，并且由于没有凸包而出现异常。 我试图模糊、扩张、精明的检测，但完全没有成功。 我希望找到使用openCV查找矩形纸/书的解决方案。 如果您还有其他问题或需要资源，请告诉我。

#include "opencv2/imgproc.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/highgui.hpp"
#include <iostream>

using namespace cv;
using namespace std;
double angle(cv::Point pt1, cv::Point pt2, cv::Point pt0) 
    double dx1 = pt1.x - pt0.x;
    double dy1 = pt1.y - pt0.y;
    double dx2 = pt2.x - pt0.x;
    double dy2 = pt2.y - pt0.y;
    return (dx1*dx2 + dy1*dy2) / sqrt((dx1*dx1 + dy1*dy1)*(dx2*dx2 + dy2*dy2) + 1e-10);


void find_squares(Mat& image, vector<vector<Point> >& squares)

    // blur will enhance edge detection
    Mat blurred(image);
    Mat dst;
    medianBlur(image, dst, 9);

    Mat gray0(dst.size(), CV_8U), gray;
    vector<vector<Point> > contours;

    // find squares in every color plane of the image
    for (int c = 0; c < 3; c++)
    
        int ch[] =  c, 0 ;
        mixChannels(&dst, 1, &gray0, 1, ch, 1);

        // try several threshold levels
        const int threshold_level = 2;
        for (int l = 0; l < threshold_level; l++)
        
            // Use Canny instead of zero threshold level!
            // Canny helps to catch squares with gradient shading
            if (l == 0)
            
                Canny(gray0, gray, 10, 20, 3); // 

                                               // Dilate helps to remove potential holes between edge segments
                dilate(gray, gray, Mat(), Point(-1, -1));
            
            else
            
                gray = gray0 >= (l + 1) * 255 / threshold_level;
            

            // Find contours and store them in a list
            findContours(gray, contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE);

            // Test contours
            vector<Point> approx;
            for (size_t i = 0; i < contours.size(); i++)
            
                // approximate contour with accuracy proportional
                // to the contour perimeter
                approxPolyDP(Mat(contours[i]), approx, arcLength(Mat(contours[i]), true)*0.02, true);

                // Note: absolute value of an area is used because
                // area may be positive or negative - in accordance with the
                // contour orientation
                if (approx.size() == 4 &&
                    fabs(contourArea(Mat(approx))) > 1000 &&
                    isContourConvex(Mat(approx)))
                
                    double maxCosine = 0;

                    for (int j = 2; j < 5; j++)
                    
                        double cosine = fabs(angle(approx[j % 4], approx[j - 2], approx[j - 1]));
                        maxCosine = MAX(maxCosine, cosine);
                    

                    if (maxCosine < 0.3)
                        squares.push_back(approx);
                
            
        
    



cv::Mat debugSquares(std::vector<std::vector<cv::Point> > squares, cv::Mat image)

    for (int i = 0; i< squares.size(); i++) 
        // draw contour
        cv::drawContours(image, squares, i, cv::Scalar(255, 0, 0), 1, 8, std::vector<cv::Vec4i>(), 0, cv::Point());

        // draw bounding rect
        cv::Rect rect = boundingRect(cv::Mat(squares[i]));
        cv::rectangle(image, rect.tl(), rect.br(), cv::Scalar(0, 255, 0), 2, 8, 0);

        // draw rotated rect
        cv::RotatedRect minRect = minAreaRect(cv::Mat(squares[i]));
        cv::Point2f rect_points[4];
        minRect.points(rect_points);
        for (int j = 0; j < 4; j++) 
            cv::line(image, rect_points[j], rect_points[(j + 1) % 4], cv::Scalar(0, 0, 255), 1, 8); // blue
        
    

    return image;



static std::vector<cv::Point> extremePoints(std::vector<cv::Point>pts)

    int  xmin = 0, ymin = 0, xmax = -1, ymax = -1, i;
    Point ptxmin, ptymin, ptxmax, ptymax;

    Point pt = pts[0];

    ptxmin = ptymin = ptxmax = ptymax = pt;
    xmin = xmax = pt.x;
    ymin = ymax = pt.y;

    for (size_t i = 1; i < pts.size(); i++)
    
        pt = pts[i];

        if (xmin > pt.x)
        
            xmin = pt.x;
            ptxmin = pt;
        


        if (xmax < pt.x)
        
            xmax = pt.x;
            ptxmax = pt;
        

        if (ymin > pt.y)
        
            ymin = pt.y;
            ptymin = pt;
        

        if (ymax < pt.y)
        
            ymax = pt.y;
            ptymax = pt;
        
    
    std::vector<cv::Point> res;
    res.push_back(ptxmin);
    res.push_back(ptxmax);
    res.push_back(ptymin);
    res.push_back(ptymax);
    return res;


void sortCorners(std::vector<cv::Point2f>& corners)


    std::vector<cv::Point2f> top, bot;
    cv::Point2f center;
    // Get mass center
    for (int i = 0; i < corners.size(); i++)
        center += corners[i];
    center *= (1. / corners.size());

    for (int i = 0; i < corners.size(); i++)
    
        if (corners[i].y < center.y)
            top.push_back(corners[i]);
        else
            bot.push_back(corners[i]);
    
    corners.clear();

    if (top.size() == 2 && bot.size() == 2) 
        cv::Point2f tl = top[0].x > top[1].x ? top[1] : top[0];
        cv::Point2f tr = top[0].x > top[1].x ? top[0] : top[1];
        cv::Point2f bl = bot[0].x > bot[1].x ? bot[1] : bot[0];
        cv::Point2f br = bot[0].x > bot[1].x ? bot[0] : bot[1];


        corners.push_back(tl);
        corners.push_back(tr);
        corners.push_back(br);
        corners.push_back(bl);
    



int main(int, char**)

    int largest_area = 0;
    int largest_contour_index = 0;
    cv::Rect bounding_rect;
    Mat src, edges;
    src = imread("20628991_10159154614610574_1244594322_o.jpg");


    cvtColor(src, edges, COLOR_BGR2GRAY);
    GaussianBlur(edges, edges, Size(5, 5), 1.5, 1.5);

    erode(edges, edges, Mat());// these lines may need to be optimized 
    dilate(edges, edges, Mat());
    dilate(edges, edges, Mat());
    erode(edges, edges, Mat());

    Canny(edges, edges, 150, 150, 3); // canny parameters may need to be optimized 
    imshow("edges", edges);

    vector<Point> selected;
    vector<vector<Point> > contours;
    findContours(edges, contours, RETR_LIST, CHAIN_APPROX_SIMPLE);

    for (size_t i = 0; i < contours.size(); i++)
    
        Rect minRect = boundingRect(contours[i]);

        if (minRect.width > 150 & minRect.height > 150) // this line also need to be optimized 
        
            selected.insert(selected.end(), contours[i].begin(), contours[i].end());
        
    

    convexHull(selected, selected);

    RotatedRect minRect = minAreaRect(selected);
    std::vector<cv::Point> corner_points = extremePoints(selected);
    std::vector<cv::Point2f> corners;

    corners.push_back(corner_points[0]);
    corners.push_back(corner_points[1]);
    corners.push_back(corner_points[2]);
    corners.push_back(corner_points[3]);

    sortCorners(corners);

    cv::Mat quad = cv::Mat::zeros(norm(corners[1] - corners[2]), norm(corners[2] - corners[3]), CV_8UC3);

    std::vector<cv::Point2f> quad_pts;
    quad_pts.push_back(cv::Point2f(0, 0));
    quad_pts.push_back(cv::Point2f(quad.cols, 0));
    quad_pts.push_back(cv::Point2f(quad.cols, quad.rows));
    quad_pts.push_back(cv::Point2f(0, quad.rows));

    cv::Mat transmtx = cv::getPerspectiveTransform(corners, quad_pts);
    cv::warpPerspective(src, quad, transmtx, quad.size());
    resize(quad, quad, Size(), 0.25, 0.25); // you can remove this line to keep the image original size
    imshow("quad", quad);

    polylines(src, selected, true, Scalar(0, 0, 255), 2);

    resize(src, src, Size(), 0.5, 0.5); // you can remove this line to keep the image original size
    imshow("result", src);
    waitKey(0); 


    return 0;

【参考方案1】：

奇怪，我就是这样做的（模糊、扩张、精巧）：

代码（在 Python 中，但除了 OpenCV 函数调用之外什么都没有，所以应该很容易理解；作为我使用的 C++ 中的 this answer 的参考之一，它还显示了如何纠正透视和转向它变成一个矩形）：

import numpy as np
import cv2

img = cv2.imread('sngo1.jpg')

#resize and create a copy for future drawing
resize_coeff = 0.5
w, h, c = img.shape
img_in = cv2.resize(img, (int(resize_coeff*h), int(resize_coeff*w)))
img_out = img_in.copy()

#median and canny
img_in = cv2.medianBlur(img_in, 5)
img_in = cv2.Canny(img_in, 100, 200)

#morphological close for our edges
kernel = np.ones((17, 17), np.uint8)
img_in = cv2.morphologyEx(img_in, cv2.MORPH_CLOSE, kernel, iterations = 1)

#find contours, get max by area
img_in, contours, hierarchy = cv2.findContours(img_in, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
max_index, max_area = max(enumerate([cv2.contourArea(x) for x in contours]), key = lambda x: x[1])
max_contour = contours[max_index]

#approximage it with a quadrangle
approx = cv2.approxPolyDP(max_contour, 0.1*cv2.arcLength(max_contour, True), True)
approx = approx[:,0,:]

cv2.drawContours(img_out, [approx], 0, (255, 0, 0), 2)
cv2.imwrite("result.png", img_out)