Tesseract5+OpenCV4（VS2017+win10）实现OCR识别

Posted 2023-03-16 GreenOpen专注CV

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了Tesseract5+OpenCV4（VS2017+win10）实现OCR识别相关的知识，希望对你有一定的参考价值。

这种环境配置方法以数量级的方式降低了环境配置的难度，而且“正好”有这样的一个可以使用的环境，从而可以快速使用opencv和tesseract等。

一、环境配置

较之前采用cppan进行编译的方式，vcpkg的方式已经发生了许多变化，带来的最大不同就是便捷。

对于在NuGet中能够找到的Vcpkg的export，真的实现了开箱即用

这样的话对于普通用户来说就购了；而复杂的问题就交给专家来解决。

二、代码编写和结果展示

// ConsoleOCRDEMO.cpp : 基于vcpkg+nuget快速解决环境配置问题
#include <opencv2/opencv.hpp>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <leptonica/allheaders.h>
#include <tesseract/baseapi.h>
#include <tesseract/publictypes.h>
using namespace cv;
using namespace cv::dnn;
using namespace std;
//对east的结果进行解码
void decode(const Mat& scores, const Mat& geometry, float scoreThresh,
    std::vector<RotatedRect>& detections, std::vector<float>& confidences)

    detections.clear();
    CV_Assert(scores.dims == 4); CV_Assert(geometry.dims == 4); CV_Assert(scores.size[0] == 1);
    CV_Assert(geometry.size[0] == 1); CV_Assert(scores.size[1] == 1); CV_Assert(geometry.size[1] == 5);
    CV_Assert(scores.size[2] == geometry.size[2]); CV_Assert(scores.size[3] == geometry.size[3]);
    const int height = scores.size[2];
    const int width = scores.size[3];
    for (int y = 0; y < height; ++y)

        const float* scoresData = scores.ptr<float>(0, 0, y);
        const float* x0_data = geometry.ptr<float>(0, 0, y);
        const float* x1_data = geometry.ptr<float>(0, 1, y);
        const float* x2_data = geometry.ptr<float>(0, 2, y);
        const float* x3_data = geometry.ptr<float>(0, 3, y);
        const float* anglesData = geometry.ptr<float>(0, 4, y);
        for (int x = 0; x < width; ++x)

            float score = scoresData[x];
            if (score < scoreThresh)
                continue;
            // Decode a prediction.
            // Multiple by 4 because feature maps are 4 time less than input image.
            float offsetX = x * 4.0f, offsetY = y * 4.0f;
            float angle = anglesData[x];
            float cosA = std::cos(angle);
            float sinA = std::sin(angle);
            float h = x0_data[x] + x2_data[x];
            float w = x1_data[x] + x3_data[x];
            Point2f offset(offsetX + cosA * x1_data[x] + sinA * x2_data[x],
                offsetY - sinA * x1_data[x] + cosA * x2_data[x]);
            Point2f p1 = Point2f(-sinA * h, -cosA * h) + offset;
            Point2f p3 = Point2f(-cosA * w, sinA * w) + offset;
            RotatedRect r(0.5f * (p1 + p3), Size2f(w, h), -angle * 180.0f / (float)CV_PI);
            detections.push_back(r);
            confidences.push_back(score);



int main()

    //参数和常量准备
    String model = "F:/未来项目/GOCVHelper455/GOCVHelper455/GOCVHelper455/model/frozen_east_text_detection.pb";
    std::vector<Mat> outs;
    std::vector<String> outNames(2);
    outNames[0] = "feature_fusion/Conv_7/Sigmoid";
    outNames[1] = "feature_fusion/concat_3";
    Mat  blob;
    std::vector<RotatedRect> boxes;
    std::vector<float> confidences;
    std::vector<int> indices;
    char cbuf[255];
    // 引入EAST model
    Net net = readNet(model);
    //对tesseract进行初始化操作
    tesseract::TessBaseAPI tess;
    if (tess.Init("C:/Program Files/Tesseract-OCR/tessdata", "eng"))

        std::cout << "OCRTesseract: Could not initialize tesseract." << std::endl;
        return 1;

    tess.SetVariable("tessedit_char_whitelist", "0123456789");
    Mat src = imread("F:/未来项目/OCR2023/2.jpg");
    Mat board = src.clone();//用于显示图片
    blobFromImage(src, blob, 1.0, Size(1280, 1280), Scalar(), true, false);//Scalar采用默认是设置
    net.setInput(blob);
    net.forward(outs, outNames);
    Mat scores = outs[0];
    Mat geometry = outs[1];
    decode(scores, geometry, 0.5, boxes, confidences);//注意0.5是超参数
    NMSBoxes(boxes, confidences, 0.5, 0.4, indices);
    Point2f ratio((float)src.cols / 1280, (float)src.rows / 1280);//缩放比例
    //获得最终框选结果
    for (size_t i = 0; i < indices.size(); ++i)

        RotatedRect& box = boxes[indices[i]];
        Point2f vertices[4];
        box.points(vertices);
        for (int j = 0; j < 4; ++j)

            vertices[j].x *= ratio.x;
            vertices[j].y *= ratio.y;

        Point2f* lastItemPointer = (vertices + sizeof vertices / sizeof vertices[0]);
        vector<Point2f> contour(vertices, lastItemPointer);
        Rect boundRect = boundingRect(Mat(contour));
        //对rect适当进行扩充
        boundRect = cv::Rect(boundRect.tl().x - 5, boundRect.tl().y, boundRect.width + 10, boundRect.height);
        if (boundRect.y < src.rows)

            Mat roi = src(boundRect);
            //绘制外接边线
            for (int j = 0; j < 4; ++j)
                line(board, vertices[j], vertices[(j + 1) % 4], Scalar(0, 255, 0), 1);
            rectangle(board, boundRect, Scalar(0, 0, 255));//绘制外接最小矩形
            //打印数据
            sprintf_s(cbuf, "F:/未来项目/OCR2023//roi/%d.jpg", i);//打印出来
            imwrite(cbuf, roi);
            ////将切割出来的图片输入tesseract中
            auto pixs = pixRead(cbuf);
            if (!pixs)

                std::cout << "Cannot open input file: " << std::endl;
                return 1;

            // recognize
            tess.SetImage(pixs);
            tess.Recognize(0);
            // get result and delete[] returned char* string
            std::cout << std::unique_ptr<char[]>(tess.GetUTF8Text()).get() << std::endl;
            string strOut = tess.GetUTF8Text();
            putText(board, std::unique_ptr<char[]>(tess.GetUTF8Text()).get(), boundRect.tl(), 1, 1.0f, Scalar(0, 255, 0));
            // cleanup
            tess.Clear();
            pixDestroy(&pixs);


    imshow("board", board);
    imwrite("F:/未来项目/OCR2023/roi/result.jpg", board);
    cv::waitKey();
    getchar();
    return 0;