亲宝软件园·资讯

展开

Python实现多个圆和圆中圆的检测

天人合一peng 人气:0

主要思想是先检测外边圆和圆心

然后再外圆内检测小圆,计算小圆圆心与外圆圆心的距离判断是不是有问题

或者可以计算两圆圆心的距离

# coding:utf-8
import math
import cv2
import numpy as np
import os
 
 
 
def findNeedlePoints(img):
    gray_src= cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    minThreshValue = 50
    _, gray = cv2.threshold(gray_src, minThreshValue, 255, cv2.THRESH_BINARY)
    erosion_size = 3
    # element = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2 * erosion_size + 1, 2 * erosion_size + 1),
    #                                     (erosion_size, erosion_size))
    element = cv2.getStructuringElement(cv2.MORPH_ERODE, (2 * erosion_size + 1, 2 * erosion_size + 1),
                                        (erosion_size, erosion_size))
    # MORPH_ELLIPSE 不同的测试一下
    erosion_gray = cv2.erode(gray, element, 3)
 
    cv2.imshow("erosion_gray", erosion_gray)
 
    paramsIn = cv2.SimpleBlobDetector_Params()
    paramsIn.filterByArea = True
 
    # 不同图片应该调节的参数
    paramsIn.minArea = 80
    paramsIn.maxArea = 1000
    paramsIn.minDistBetweenBlobs = 80
    paramsIn.filterByColor = True
    paramsIn.filterByConvexity = False
    paramsIn.minThreshold = 100*2
    paramsIn.maxThreshold = 1000
 
    # 图像取反
    needleGray = 255 - erosion_gray.copy()
    # 中值滤波和腐蚀去噪
    needleGray = cv2.medianBlur(needleGray, 3)
 
    # cv2.imshow('needleGray', needleGray)
 
 
    erosion_size = 2
    element = cv2.getStructuringElement(cv2.MORPH_RECT, (2 * erosion_size + 1, 2 * erosion_size + 1),
                                        (erosion_size, erosion_size))
    needlePoints = cv2.erode(needleGray, element, 1)
    cv2.imshow('needle=Points', needlePoints)
 
    detector2 = cv2.SimpleBlobDetector_create(paramsIn)
    needleKeypoints = detector2.detect(needlePoints)
    # opencv
    needle_keypoints = cv2.drawKeypoints(needlePoints, needleKeypoints, np.array([]), (255, 0, 0),
                                         cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
 
    allNeedlePoints = []
    if needleKeypoints is not None:
        for i in range(len(needleKeypoints)):
            allNeedlePoints.append(needleKeypoints[i].pt)
 
    color_img = cv2.cvtColor(needle_keypoints, cv2.COLOR_BGR2RGB)
    # needle_img = cv2.cvtColor(im_with_keypoints, cv2.COLOR_BGR2RGB)
 
    cv2.imshow('holeShow', color_img)
    # cv2.imshow('needleShow', needle_img)
 
    cv2.waitKey()
 
 
 
def innerHoughCicle(hsv_image, src_image, rect):
    # 霍夫变换圆检测
 
    gray_src = cv2.cvtColor(hsv_image, cv2.COLOR_HSV2RGB)
    gray_src = cv2.cvtColor(gray_src, cv2.COLOR_RGB2GRAY)
    minThreshValue = 100
    _, gray = cv2.threshold(gray_src, minThreshValue, 255, cv2.THRESH_BINARY)
 
    kernel1 = np.ones((3, 3), dtype=np.uint8)
    kernel2 = np.ones((3, 3), dtype=np.uint8)
 
    gray = cv2.erode(gray, kernel2, 2)
    gray = cv2.dilate(gray, kernel1, 2)  # 1:迭代次数,也就是执行几次膨胀操作
 
    # cv2.namedWindow("gray", 2)
    # cv2.imshow("gray", gray)
    # cv2.waitKey()
    circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 2, 100, param1=100, param2=60, minRadius=10, maxRadius=100)
    # 如果没检测到会报错
    # 这种判断方式过于简单
    if circles is None:
        print("没有检测到连接器外圆")
 
    else:
        for circle in circles[0]:
            # 圆的基本信息
            # print(circle[2])
            # 坐标行列-圆心坐标
            out_x = int(circle[0])
            out_y = int(circle[1])
            # 半径
            r = int(circle[2])
            # # 在原图用指定颜色标记出圆的边界
            cv2.circle(hsv_image, (out_x, out_y), r, (0, 0, 255), 2)
            # # 画出圆的圆心
            cv2.circle(hsv_image, (out_x, out_y), 3, (0, 0, 255), -1)
 
 
 
 
        cv2.namedWindow("hsv_circle", 2)
        cv2.imshow("hsv_circle",hsv_image)
        cv2.waitKey()
 
def outHoughCicle(hsv_image, src_image, rect):
    # 霍夫变换圆检测
 
    gray_src = cv2.cvtColor(hsv_image, cv2.COLOR_HSV2RGB)
    gray_src = cv2.cvtColor(gray_src, cv2.COLOR_RGB2GRAY)
    minThreshValue = 50
    _, gray = cv2.threshold(gray_src, minThreshValue, 255, cv2.THRESH_BINARY)
 
    kernel1 = np.ones((3, 3), dtype=np.uint8)
    kernel2 = np.ones((3, 3), dtype=np.uint8)
 
    gray = cv2.erode(gray, kernel2, 2)
    gray = cv2.dilate(gray, kernel1, 2)  # 1:迭代次数,也就是执行几次膨胀操作
 
    cv2.namedWindow("gray", 2)
    cv2.imshow("gray", gray)
    cv2.waitKey()
    circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1, 10e10, param1=100, param2=60, minRadius=500, maxRadius=10000)
    # 如果没检测到会报错
    # 这种判断方式过于简单
    if circles is None:
        print("没有检测到连接器外圆")
 
    else:
        for circle in circles[0]:
            # 圆的基本信息
            # print(circle[2])
            # 坐标行列-圆心坐标
            out_x = int(circle[0])
            out_y = int(circle[1])
            # 半径
            r = int(circle[2])
            # # 在原图用指定颜色标记出圆的边界
            cv2.circle(hsv_image, (out_x, out_y), r, (0, 0, 255), 2)
            # # 画出圆的圆心
            cv2.circle(hsv_image, (out_x, out_y), 3, (0, 0, 255), -1)
 
            # 画在原图上
            cv2.circle(src_image, (out_x + rect[0], out_y + rect[1]), r, (0, 0, 255), 2)
            # # 画出圆的圆心
            cv2.circle(src_image, (out_x + rect[0], out_y+ rect[1]), 3, (0, 0, 255), -1)
 
 
        cv2.namedWindow("hsv_circle", 2)
        cv2.imshow("hsv_circle",hsv_image)
 
        cv2.namedWindow("src_image", 2)
        cv2.imshow("src_image",src_image)
        cv2.waitKey()
 
 
 
# 检测针脚位置
def needelCenter_detect(img):
    params = cv2.SimpleBlobDetector_Params()
    # Setup SimpleBlobDetector parameters.
    # print('params')
    # print(params)
    # print(type(params))
 
    # Filter by Area.
    params.filterByArea = True
    params.minArea = 100
    params.maxArea = 10e3
    params.minDistBetweenBlobs = 50
    # params.filterByColor = True
    params.filterByConvexity = False
    # tweak these as you see fit
    # Filter by Circularity
    params.filterByCircularity = False
    params.minCircularity = 0.2
    # params.blobColor = 0
    # # # Filter by Convexity
    # params.filterByConvexity = True
    # params.minConvexity = 0.87
    # Filter by Inertia
    # params.filterByInertia = True
    # params.filterByInertia = False
    # params.minInertiaRatio = 0.01
 
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 
    # Detect blobs.
    minThreshValue = 100
    _, gray = cv2.threshold(gray, minThreshValue, 255, cv2.THRESH_BINARY)
 
    erosion_size = 1
    # element = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2 * erosion_size + 1, 2 * erosion_size + 1),
    #                                     (erosion_size, erosion_size))
    element = cv2.getStructuringElement(cv2.MORPH_ERODE, (2 * erosion_size + 1, 2 * erosion_size + 1),
                                        (erosion_size, erosion_size))
    dilate_gray = cv2.dilate(gray, element, 1)
 
    # cv2.namedWindow("gray", 2)
    # cv2.imshow("gray",dilate_gray)
    # cv2.waitKey()
 
    detector = cv2.SimpleBlobDetector_create(params)
    keypoints = detector.detect(dilate_gray)
    # print(len(keypoints))
    # print(keypoints[0].pt[0])
    # 如果这儿没检测到可能会出错
    if len(keypoints) == 0:
        print("没有检测到针角坐标,可能需要调整针角斑点检测参数")
        print(keypoints)
        return keypoints
 
    else:
        print("检测到孔的数量", len(keypoints))
        # im_with_keypoints = cv2.drawKeypoints(img, keypoints, np.array([]), (255, 0, 0),
        #                                       cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
        #
        # color_img = cv2.cvtColor(im_with_keypoints, cv2.COLOR_BGR2RGB)
        # 画出圆的圆心
        # for kp in keypoints:
        #     cv2.circle(img, (int(kp.pt[0]), int(kp.pt[1])), 3, (0, 0, 255), -1)
        #
        # cv2.namedWindow("color_img", 2)
        # cv2.imshow("color_img",img)
        # # cv2.waitKey()
 
        return keypoints
 
 
# 检测外部区域针或孔的位置
def out_circle_detect(rect_hole_info, src):
    # 灰度化
    circle_img = rect_hole_info
 
    gray = cv2.cvtColor(circle_img, cv2.COLOR_HSV2RGB)
    gray = cv2.cvtColor(gray, cv2.COLOR_RGB2GRAY)
 
    # 输出图像大小,方便根据图像大小调节minRadius和maxRadius
    # print(image.shape)
    # 进行中值滤波
    img = cv2.medianBlur(gray, 3)
 
    erosion_size = 3
    # element = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2 * erosion_size + 1, 2 * erosion_size + 1),
    #                                     (erosion_size, erosion_size))
    element = cv2.getStructuringElement(cv2.MORPH_ERODE, (2 * erosion_size + 1, 2 * erosion_size + 1),
                                        (erosion_size, erosion_size))
    dilate_gray = cv2.dilate(img, element, 1)
    # cv2.namedWindow("dilate_gray", 2)
    # cv2.imshow("dilate_gray", dilate_gray)
    # cv2.waitKey()
 
    # 针角圆心坐标
    out_x, out_y, r = 0, 0, 0
 
    # 霍夫变换检测最大圆
    circles = cv2.HoughCircles(dilate_gray, cv2.HOUGH_GRADIENT, 1, 1000, param1=100, param2=30, minRadius=500, maxRadius=1000)
    # 如果没检测到会报错
    # 这种判断方式过于简单
    if circles is None:
        print("没有检测到连接器外圆")
        return 0, 0, 0
    else:
        for circle in circles[0]:
            # 圆的基本信息
            # print(circle[2])
            # 坐标行列-圆心坐标
            out_x = int(circle[0])
            out_y = int(circle[1])
            # 将检测到的坐标保存
            # 半径
            r = int(circle[2])
            # print(r)
            # # # 在原图用指定颜色标记出圆的边界
            cv2.circle(circle_img, (out_x, out_y), r, (0, 0, 255), 2)
            # # 画出圆的圆心
            cv2.circle(circle_img, (out_x, out_y), 5, (0, 0, 255), -1)
 
        cv2.namedWindow("circle_imgs", 2)
        cv2.imshow("circle_imgs", circle_img)
        cv2.waitKey()
 
        return out_x, out_y, r
 
 
 
 
# 检测内部区域针或孔的位置
def inner_circle_detect(rect_hole_info, src):
    # 灰度化
    circle_img = rect_hole_info
 
    gray = cv2.cvtColor(circle_img, cv2.COLOR_HSV2RGB)
    gray = cv2.cvtColor(gray, cv2.COLOR_RGB2GRAY)
 
    # 输出图像大小,方便根据图像大小调节minRadius和maxRadius
    # print(image.shape)
    # 进行中值滤波
    img = cv2.medianBlur(gray, 3)
 
    erosion_size = 3
    # element = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2 * erosion_size + 1, 2 * erosion_size + 1),
    #                                     (erosion_size, erosion_size))
    element = cv2.getStructuringElement(cv2.MORPH_ERODE, (2 * erosion_size + 1, 2 * erosion_size + 1),
                                        (erosion_size, erosion_size))
    dilate_gray = cv2.dilate(img, element, 1)
    # cv2.namedWindow("dilate_gray", 2)
    # cv2.imshow("dilate_gray", dilate_gray)
    # cv2.waitKey()
 
 
    # 针角圆心坐标
    out_x_p = []
    out_y_p = []
    rudis = []
 
    # 霍夫变换检测最大圆
    circles = cv2.HoughCircles(dilate_gray, cv2.HOUGH_GRADIENT, 1, 100, param1=100, param2=30, minRadius=20, maxRadius=100)
    # 如果没检测到会报错
    # 这种判断方式过于简单
    if circles is None:
        print("没有检测到连接器外圆")
        return out_x_p, out_y_p
 
    else:
        for circle in circles[0]:
            # 圆的基本信息
            # print(circle[2])
            # 坐标行列-圆心坐标
            out_x = int(circle[0])
            out_y = int(circle[1])
            # 将检测到的坐标保存
            out_x_p.append(out_x)
            out_y_p.append(out_y)
            # 半径
            r = int(circle[2])
            rudis.append(r)
            # print(r)
            # # # 在原图用指定颜色标记出圆的边界
            cv2.circle(circle_img, (out_x, out_y), r, (0, 0, 255), 2)
            # # 画出圆的圆心
            cv2.circle(circle_img, (out_x, out_y), 5, (0, 0, 255), -1)
 
        cv2.namedWindow("circle_img", 2)
        cv2.imshow("circle_img",circle_img)
        cv2.waitKey()
 
        # 记录外圆坐标
 
        out_xpoints = out_x_p.copy()
        out_ypoints = out_y_p.copy()
        out_rudis = rudis.copy()
        # print("out_xpoints",out_xpoints)
        # print("out_ypoints",out_ypoints)
 
        # 只框出单个针角的位置区域
        step_center = 25
        step_rect = 50
 
        # 遍历所有的孔的位置
        # 记录孔的位置
        in_x_p = []
        in_y_p = []
        for i in range(0, len(out_xpoints)):
            out_x_begin = out_xpoints[i] - step_center
            out_y_begin = out_ypoints[i] - step_center
            needleRect = circle_img[out_y_begin: out_y_begin + step_rect, out_x_begin: out_x_begin + step_rect]
            # cv2.namedWindow("needleRect", 2)
            # cv2.imshow("needleRect", needleRect)
            # cv2.waitKey()
 
            # 根据检测到的圆形连接器中心找针角位置
            centerPoint = needelCenter_detect(needleRect)
            # print(len(centerPoint))
 
            if len(centerPoint) == 0:
                out_x_p.remove(out_xpoints[i])
                out_y_p.remove(out_ypoints[i])
                rudis.remove(out_rudis[i])
                print("调整位置")
            else:
                for cp in centerPoint:
                        # 将针角的坐标原还至原图
                    in_x = int(cp.pt[0])
                    in_y = int(cp.pt[1])
                    in_x += out_x_begin
                    in_y += out_y_begin
 
                    in_x_p.append(in_x)
                    in_y_p.append(in_y)
 
                # # # 画出中心孔的圆心
                #     cv2.circle(circle_img, (in_x, in_y), 4, (0, 255, 0), -1)
                #     # 画出外孔的圆心
                #     cv2.circle(circle_img, (out_xpoints[i], out_ypoints[i]), 4, (0, 0, 255), -1)
 
                # # 计算两者的距离
                #     # 假设通过标定其一个像素代表0.0056mm
                #     DPI = 0.0198
                #     dis = math.sqrt(math.pow(out_xpoints[i] - in_x,2) + math.pow(out_ypoints[i] - in_y,2))
                #     print("两者相互之间的距离为(mm):", dis*DPI)
        return in_x_p,in_y_p
 
                # cv2.namedWindow("image", 2)
                # cv2.imshow("image",circle_img)
                # cv2.waitKey()
        # if len(out_x_p) == 0:
        #     print("没检测到,需要调整位置")
        # else:
        #     for j in range(0,len(out_x_p)):
        #         # 画出外孔的圆心
        #         cv2.circle(circle_img, (out_x_p[j], out_y_p[j]), rudis[j], (0, 0, 255), 3)
        #         cv2.circle(circle_img, (out_x_p[j], out_y_p[j]), 3, (0, 0, 255), -1)
        #
        #         # cv2.circle(circle_img, (in_x_p[j], in_y_p[j]), 3, (0, 255, 0), -1)
        #
        #     cv2.namedWindow("image", 2)
        #     cv2.imshow("image",circle_img)
        #     cv2.waitKey()
 
 
 
def j599_4_holes_dectWX(imagePath, templatePath):
    # templatePath需要用户手动框获取ROI
    img = cv2.imread(imagePath)
    img_roi = cv2.imread(templatePath)
 
    if img_roi is  None:
        print("no image")
 
    # HSV二值化
    img_roi = cv2.medianBlur(img_roi, 5)  # 中值滤波
    outx, outy, outR = out_circle_detect(img_roi, img)
    print(outx, outy, outR )
    inx, iny = inner_circle_detect(img_roi, img)
    if len(inx) == 0 or outx == 0:
        print("没检测到位置")
        return "没检测到对象", -1
    else:
        cv2.circle(img_roi, (outx, outy), outR, (0, 0, 255), 3)
 
        is_ok = []
 
        for k in range(0, len(inx)):
            # 计算两者的距离
            # 假设通过标定其一个像素代表0.0056mm
            # 两者相互之间的距离为(mm): 9.311053946788194
            # 两者相互之间的距离为(mm): 9.163550379629067
            # 两者相互之间的距离为(mm): 8.95984457900917
            # 两者相互之间的距离为(mm): 8.977940966613671
            # 平均值为 9.103 所以其阈值为9.103 + 0.5
            DPI = 0.0198
            dis = math.sqrt(math.pow(outx - inx[k], 2) + math.pow(outy - iny[k], 2))
            dis *= DPI
            # print("两者相互之间的距离为(mm):", dis)
            if dis < 9.603:
                cv2.circle(img_roi, (inx[k], iny[k]), 8, (0, 255, 0), -1)
                # print("没有插针歪斜,产品合格")
                is_ok.append(1)
            else:
                cv2.circle(img_roi, (inx[k], iny[k]), 20, (0, 0, 255), 3)
                # print("有插针歪斜,不合格")
                is_ok.append(0)
 
        # cv2.namedWindow("image", 2)
        # cv2.imshow("image",img_roi)
        # cv2.waitKey()
 
        isExists = os.path.exists("./runs/J599/")
        if not isExists:
            os.makedirs("./runs/J599/")
        cv2.imwrite("./runs/J599/result.jpg", img_roi)
 
        if 0 in is_ok:
            print("有插针歪斜,不合格")
            return "有插针歪斜,不合格"
        else:
            print("没有插针歪斜,产品合格")
            return "没有插针歪斜,产品合格"
 
 
 
 
if __name__ == "__main__":
    reslut = j599_4_holes_dectWX("images/Final/E_0_8.jpg","J599-4holes_template.jpg")
    print(reslut)
#
#     # # # 4holes
#     img = cv2.imread("images/Final/E_0_8.jpg", 1)
#     # img_roi = img[973:2027, 1713:2751]
#     # img_roi = img[852:2224, 1515:2940]
#     img_roi = img[842:2234, 1480:2950]
#     cv2.imwrite("J599-4holes_template.jpg",img_roi)
#
#     # cv2.namedWindow("img_roi",2)
#     # cv2.imshow("img_roi", img_roi)
#     # cv2.waitKey()
 
#     if img_roi is  None:
#         print("no image")
#     else:
#         # HSV二值化
#         img_roi = cv2.medianBlur(img_roi, 5)  # 中值滤波
#         outx, outy, outR = out_circle_detect(img_roi, img)
#         print(outx, outy, outR )
#         inx, iny = inner_circle_detect(img_roi, img)
#         if len(inx) == 0 or outx == 0:
#             print("没检测到位置")
#         else:
#             cv2.circle(img_roi, (outx, outy), outR, (0, 0, 255), 3)
#
#             for k in range(0, len(inx)):
#                 # 计算两者的距离
#                 # 假设通过标定其一个像素代表0.0056mm
#                 # 两者相互之间的距离为(mm): 9.311053946788194
#                 # 两者相互之间的距离为(mm): 9.163550379629067
#                 # 两者相互之间的距离为(mm): 8.95984457900917
#                 # 两者相互之间的距离为(mm): 8.977940966613671
#                 # 平均值为 9.103 所以其阈值为9.103 + 0.5
#                 DPI = 0.0198
#                 dis = math.sqrt(math.pow(outx - inx[k], 2) + math.pow(outy - iny[k], 2))
#                 dis *= DPI
#                 # print("两者相互之间的距离为(mm):", dis)
#                 if dis > 9.603:
#                     cv2.circle(img_roi, (inx[k], iny[k]), 20, (0, 0, 255), 3)
#                     print("有插针歪斜,不合格")
#                 else:
#                     cv2.circle(img_roi, (inx[k], iny[k]), 8, (0, 255, 0), -1)
#                     print("没有插针歪斜,产品合格")
#
#             cv2.namedWindow("image", 2)
#             cv2.imshow("image",img_roi)
#             cv2.waitKey()

加载全部内容

相关教程
猜你喜欢
用户评论