轻松上手场景文字检测——EAST模型使用 | 【双语实现】

Net cv::dnn::readNet(
const String &     model,
const String &     config = "",
const String &     framework = "" 
)
model表示模型路径
config表示配置文件，缺省为空
framework表示框架，缺省为空，根据导入模型自己决定

void cv::dnn::NMSBoxes(
    const std::vector< Rect > &     bboxes,
    const std::vector< float > &    scores,
    const float     score_threshold,
    const float     nms_threshold,
    std::vector< int > &    indices,
    const float     eta = 1.f,
    const int   top_k = 0 
)
Bboxes表示输入的boxes
Score表示每个box得分
score_threshold表示score的阈值
nms_threshold表示非最大抑制阈值
indices表示输出的结果，是每个box的索引index数组
eta表示自适应的阈值nms阈值方式
top_k表示前多少个，为0表示忽略

#include <opencv2/opencv.hpp>>
#include <opencv2/dnn.hpp>

using namespace cv;
using namespace cv::dnn;

void decode(const Mat& scores, const Mat& geometry, float scoreThresh,
    std::vector<RotatedRect>& detections, std::vector<float>& confidences);

int main(int argc, char** argv)
{
    float confThreshold = 0.5;
    float nmsThreshold = 0.4;
    int inpWidth = 320;
    int inpHeight = 320;
    String model = "D:/python/cv_demo/ocr_demo/frozen_east_text_detection.pb";

    // Load network.
    Net net = readNet(model);

    // Open a camera stream.
    VideoCapture cap(0);

    static const std::string kWinName = "EAST: An Efficient and Accurate Scene Text Detector";
    namedWindow(kWinName, WINDOW_AUTOSIZE);

    std::vector<Mat> outs;
    std::vector<String> outNames(2);
    outNames[0] = "feature_fusion/Conv_7/Sigmoid";
    outNames[1] = "feature_fusion/concat_3";

    Mat frame, blob;
    while (waitKey(1) < 0)
    {
        cap >> frame;
        if (frame.empty())
        {
            waitKey();
            break;
        }

        blobFromImage(frame, blob, 1.0, Size(inpWidth, inpHeight), Scalar(123.68, 116.78, 103.94), true, false);
        net.setInput(blob);
        net.forward(outs, outNames);

        Mat scores = outs[0];
        Mat geometry = outs[1];

        // Decode predicted bounding boxes.
        std::vector<RotatedRect> boxes;
        std::vector<float> confidences;
        decode(scores, geometry, confThreshold, boxes, confidences);

        // Apply non-maximum suppression procedure.
        std::vector<int> indices;
        NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);

        // Render detections.
        Point2f ratio((float)frame.cols / inpWidth, (float)frame.rows / inpHeight);
        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;
            }
            for (int j = 0; j < 4; ++j)
                line(frame, vertices[j], vertices[(j + 1) % 4], Scalar(0, 255, 0), 1);
        }

        // Put efficiency information.
        std::vector<double> layersTimes;
        double freq = getTickFrequency() / 1000;
        double t = net.getPerfProfile(layersTimes) / freq;
        std::string label = format("Inference time: %.2f ms", t);
        putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));

        imshow(kWinName, frame);
    }
    return 0;
}

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);
        }
    }
}

if __name__ == "__main__":
    text_detector = TextAreaDetector("D:/python/cv_demo/ocr_demo/frozen_east_text_detection.pb")
    frame = cv.imread("D:/txt.png")
    start = time.time()
    text_detector.detect(frame)
    end = time.time()
    print("[INFO] text detection took {:.4f} seconds".format(end - start))
    # show the output image
    cv.imshow("Text Detection", frame)
    cv.waitKey(0)
    cap = cv.VideoCapture(0)
    while True:
        ret, frame = cap.read()
        if ret is not True:
            break
        text_detector.detect(frame)
        cv.imshow("east text detect demo", frame)
        c = cv.waitKey(5)
        if c == 27:
            break
    cv.destroyAllWindows()