钢管求验收

最新推荐文章于 2024-01-21 20:38:14 发布

原创最新推荐文章于 2024-01-21 20:38:14 发布 · 263 阅读

CC 4.0 BY-SA版权

本文介绍了一种基于图像处理的钢管检测算法，通过使用Canny边缘检测和Hough圆变换，实现了对钢管的有效识别。在实验中，该算法对钢管1的检测正确率接近100%，对钢管2的检测正确率在排除错检后达到95.6%。

import cv2 as cv
import matplotlib.pyplot as plt
import numpy as np
import my_util as util
import mian
def main():
    import cv2
    import numpy as np

    filename = "images/many.jpg"
    image = cv2.imread(filename)
    radious = int(mian.find_radious(image))
    #image = cv2.imread("images/24.jpg")
    contours_img = image.copy()

    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    gray = cv.equalizeHist(gray)
    blurred = cv2.GaussianBlur(gray, (5, 5), 0)
   #cv_show('blurred', blurred)
    edged = cv2.Canny(blurred, 75, 200)
    util.image_read('edged', edged)




    #gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    #blur = cv2.medianBlur(gray, 5)
    # circles = cv2.HoughCircles(gray, cv2_HOUGH_GRADIENT, 1, 10)

    #circles = cv2.HoughCircles(edged, cv2.HOUGH_GRADIENT, 1, 30,param1=50, param2=30, minRadius=25, maxRadius=40)
    circles = cv2.HoughCircles(edged, cv2.HOUGH_GRADIENT, 1, 5+radious, param1=50, param2=20, minRadius=int(radious*0.5), maxRadius=int(radious*1.5))

    #cv2.HoughCircles(blur,cv2.HOUGH_GRADIENT , dp, minDist, circles, param1, param2, minRadius, maxRadius)

    circles = np.uint16(np.around(circles))

    for i in circles[0, :]:
        # draw the outer circle
        cv2.circle(image, (i[0], i[1]), i[2], (255, 0, 0), 2)
        # draw the center of the circle
        cv2.circle(image, (i[0], i[1]), 2, (0, 255, 0), 5)

    cv2.imshow('detected circles', image)
    cv2.waitKey(0)
    cv2.destroyAllWindows()
    print("钢管数目为：",len(circles[0,:]))

if __name__ == '__main__':
    main()

try_1.py

钢管1：