Halcon实现

思路：

通过中值滤波后，对图像进行动态阈值提取细化缺陷部分，结合开运算，闭运算提取缺陷。

read_image (Image, 'D:/opencv练习图片/复杂背景提取缺陷.jpg')

dev_set_line_width (3)

threshold (Image, Region, 30, 255)

reduce_domain (Image, Region, ImageReduced)

mean_image (ImageReduced, ImageMean, 150, 150)

dyn_threshold (ImageReduced, ImageMean, SmallRaw, 37, 'dark')

opening_circle (SmallRaw, RegionOpening,4.5)

closing_circle (RegionOpening, RegionClosing, 7)

connection (RegionClosing, ConnectedRegions)

dev_set_color ('red')

dev_display (Image)

dev_set_draw ('margin')

dev_display (ConnectedRegions)

 Opencv实现

 实现方法与思路:

原图转灰度图后使用核大小201（奇数）做中值滤波；

灰度图与滤波图像做差,阈值处理

形态学进一步提取缺陷

轮廓查找，通过面积筛选缺陷，显示

大林上位机机器视觉，_常州电工培训_常州PLC培训_常州机器视觉培训_常州上位机培训_常州工业机器人培训，最适合电工及plc编程人员学习的上位机机器视觉课程 大林老师：15861139266（微信同号）

int main(int argc, char** argv)

{

    Mat src = imread("D:/opencv练习图片/复杂背景提取缺陷.jpg");

    imshow("输入图像", src);

    Mat gray, gray_mean,dst,binary1, binary2, binary;

    cvtColor(src, gray, COLOR_BGR2GRAY);

    medianBlur(gray, gray_mean, 201);

    imshow("中值滤波", gray_mean);

    addWeighted(gray, -1, gray_mean, 1, 0, dst);

    imshow("做差", dst);

    //阈值提取

    threshold(dst, binary1, 10, 255, THRESH_BINARY|THRESH_OTSU);

    imshow("二值化", binary1);

    Mat src_open, src_close;

    //形态学

    Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(7, 7), Point(-1, -1));

    morphologyEx(binary1, src_open, MORPH_OPEN, kernel, Point(-1, -1));

    imshow("开运算", src_open);

    morphologyEx(src_open, src_close, MORPH_CLOSE, kernel, Point(-1, -1));

    imshow("闭运算", src_close);

    vector<vector<Point>>contours;

    findContours(src_close, contours, RETR_EXTERNAL, CHAIN_APPROX_NONE, Point());

    for (int i = 0; i < contours.size(); i++)

    {

        float area = contourArea(contours[i]);

        cout << area << endl;

        if (area > 1000)

        {

            drawContours(src, contours, i, Scalar(0, 0, 255), 2, 8);

        }

    }

    imshow("结果", src);

    waitKey(0);

    return 0;

}