java - 图像处理与字符提取

Question

我正在尝试找出处理角色图像所需的技术。

具体来说，在这个例子中，我需要提取被圈出的主题标签。你可以在这里看到它:

任何实现都会有很大帮助。

Answer 1

可以用 OpenCV 解决这个问题+ Tesseract

虽然我认为可能有更简单的方法。 OpenCV 是一个用于构建计算机视觉应用程序的开源库，Tesseract 是一个开源 OCR 引擎。

在我们开始之前，让我澄清一点:那不是一个圆，它是一个圆角矩形。

我正在分享我为演示如何解决问题而编写的应用程序的源代码，以及一些关于正在发生的事情的提示。这个答案不应该对任何人进行数字图像处理方面的教育，并且希望读者对该领域有最低限度的了解。

我将非常简要地描述代码的较大部分的作用。接下来的大部分代码来自squares.cpp ，一个随 OpenCV 一起提供的示例应用程序，用于检测图像中的正方形。

#include <iostream>
#include <vector>

#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>

// angle: helper function.
// Finds a cosine of angle between vectors from pt0->pt1 and from pt0->pt2.
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);
}

// findSquares: returns sequence of squares detected on the image.
// The sequence is stored in the specified memory storage.
void findSquares(const cv::Mat& image, std::vector<std::vector<cv::Point> >& squares)
{  
    cv::Mat pyr, timg;

    // Down-scale and up-scale the image to filter out small noises
    cv::pyrDown(image, pyr, cv::Size(image.cols/2, image.rows/2));
    cv::pyrUp(pyr, timg, image.size());

    // Apply Canny with a threshold of 50
    cv::Canny(timg, timg, 0, 50, 5);

    // Dilate canny output to remove potential holes between edge segments
    cv::dilate(timg, timg, cv::Mat(), cv::Point(-1,-1));

    // find contours and store them all as a list 
    std::vector<std::vector<cv::Point> > contours;           
    cv::findContours(timg, contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE);

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

        // Square contours should have 4 vertices after approximation
        // relatively large area (to filter out noisy contours)
        // and be convex.
        // 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(cv::contourArea(cv::Mat(approx))) > 1000 &&
            cv::isContourConvex(cv::Mat(approx)) )
        {
            double maxCosine = 0;

            for (int j = 2; j < 5; j++)
            {
                // Find the maximum cosine of the angle between joint edges
                double cosine = fabs(angle(approx[j%4], approx[j-2], approx[j-1]));
                maxCosine = MAX(maxCosine, cosine);
            }

            // If cosines of all angles are small
            // (all angles are ~90 degree) then write quandrange
            // vertices to resultant sequence
            if( maxCosine < 0.3 )
                squares.push_back(approx);
        }
    }         
}


// drawSquares: function draws all the squares found in the image
void drawSquares( cv::Mat& image, const std::vector<std::vector<cv::Point> >& squares )
{
    for( size_t i = 0; i < squares.size(); i++ )
    {
        const cv::Point* p = &squares[i][0];
        int n = (int)squares[i].size();
        cv::polylines(image, &p, &n, 1, true, cv::Scalar(0,255,0), 2, CV_AA);
    }

    cv::imshow("drawSquares", image);
}

好的，所以我们的程序开始于:

int main(int argc, char* argv[])
{
// Load input image (colored, 3-channel)
cv::Mat input = cv::imread(argv[1]);
if (input.empty())
{
    std::cout << "!!! failed imread()" << std::endl;
    return -1;
}   

// Convert input image to grayscale (1-channel)
cv::Mat grayscale = input.clone();
cv::cvtColor(input, grayscale, cv::COLOR_BGR2GRAY);
//cv::imwrite("gray.png", grayscale);

灰度是什么样子的:

// Threshold to binarize the image and get rid of the shoe
cv::Mat binary;
cv::threshold(grayscale, binary, 225, 255, cv::THRESH_BINARY_INV);
cv::imshow("Binary image", binary);
//cv::imwrite("binary.png", binary);

二进制是什么样的:

// Find the contours in the thresholded image
std::vector<std::vector<cv::Point> > contours;
cv::findContours(binary, contours, cv::RETR_LIST, cv::CHAIN_APPROX_SIMPLE);

// Fill the areas of the contours with BLUE (hoping to erase everything inside a rectangular shape)
cv::Mat blue = input.clone();      
for (size_t i = 0; i < contours.size(); i++)
{
    std::vector<cv::Point> cnt = contours[i];
    double area = cv::contourArea(cv::Mat(cnt));               

    //std::cout << "* Area: " << area << std::endl; 
    cv::drawContours(blue, contours, i, cv::Scalar(255, 0, 0), 
                     CV_FILLED, 8, std::vector<cv::Vec4i>(), 0, cv::Point() );         
}       

cv::imshow("Countours Filled", blue);  
//cv::imwrite("contours.png", blue);  

蓝色是什么样子的:

// Convert the blue colored image to binary (again), and we will have a good rectangular shape to detect
cv::Mat gray;
cv::cvtColor(blue, gray, cv::COLOR_BGR2GRAY);
cv::threshold(gray, binary, 225, 255, cv::THRESH_BINARY_INV);
cv::imshow("binary2", binary);
//cv::imwrite("binary2.png", binary);

二进制此时的样子:

// Erode & Dilate to isolate segments connected to nearby areas
int erosion_type = cv::MORPH_RECT; 
int erosion_size = 5;
cv::Mat element = cv::getStructuringElement(erosion_type, 
                                            cv::Size(2 * erosion_size + 1, 2 * erosion_size + 1), 
                                            cv::Point(erosion_size, erosion_size));
cv::erode(binary, binary, element);
cv::dilate(binary, binary, element);
cv::imshow("Morphologic Op", binary); 
//cv::imwrite("morpho.png", binary);

二进制此时的样子:

// Ok, let's go ahead and try to detect all rectangular shapes
std::vector<std::vector<cv::Point> > squares;
findSquares(binary, squares);
std::cout << "* Rectangular shapes found: "  << squares.size() << std::endl;

// Draw all rectangular shapes found
cv::Mat output = input.clone();
drawSquares(output, squares);
//cv::imwrite("output.png", output);

输出是什么样的:

好的!我们解决了问题的第一部分，即找到圆角矩形。您可以在上图中看到检测到矩形形状，并且出于教育目的在原始图像上绘制了绿线。

第二部分要容易得多。它首先在原始图像中创建一个 ROI(感兴趣区域)，以便我们可以将图像裁剪到圆角矩形内的区域。完成此操作后，裁剪后的图像将作为 TIFF 文件保存在磁盘上，然后将其馈送到 Tesseract，这很神奇:

// Crop the rectangular shape
if (squares.size() == 1)
{    
    cv::Rect box = cv::boundingRect(cv::Mat(squares[0]));
    std::cout << "* The location of the box is x:" << box.x << " y:" << box.y << " " << box.width << "x" << box.height << std::endl;

    // Crop the original image to the defined ROI
    cv::Mat crop = input(box);
    cv::imshow("crop", crop);
    //cv::imwrite("cropped.tiff", crop);
}
else
{
    std::cout << "* Abort! More than one rectangle was found." << std::endl;
}

// Wait until user presses key
cv::waitKey(0);

return 0;
}

裁剪是什么样子的:

当这个应用程序完成它的工作时，它会在磁盘上创建一个名为 cropped.tiff 的文件。转到命令行并调用 Tesseract 来检测裁剪图像上存在的文本:

tesseract cropped.tiff out

此命令使用检测到的文本创建一个名为 out.txt 的文件:

Tesseract 有一个 API，您可以使用该 API 将 OCR 功能添加到您的应用程序中。

此解决方案并不可靠，您可能必须在各处进行一些更改才能使其适用于其他测试用例。