通過模闆比對先定位檢測的對象再檢測圓形零件和孔針03

import os
import cv2
import numpy as np
import math
import xml.etree.ElementTree as ET
# import imutils
# 檢測針腳位置
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 = 10
    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


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

    # Detect blobs.
    minThreshValue = 110
    _, gray = cv2.threshold(gray, minThreshValue, 255, cv2.THRESH_BINARY)

    detector = cv2.SimpleBlobDetector_create(params)
    gray = 255 - gray
    keypoints = detector.detect(gray)
    # print(len(keypoints))
    # print(keypoints[0].pt[0])
    # 如果這兒沒檢測到可能會出錯
    if len(keypoints) == 0:
        print("沒有檢測到針角坐标，可能需要調整針角斑點檢測參數")
        return keypoints
    else:
        # print(len(keypoints))
        # im_with_keypoints = cv2.drawKeypoints(gray, keypoints, np.array([]), (255, 0, 0),
        #                                       cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)

        # if keypoints is not None:

        # color_img = cv2.cvtColor(im_with_keypoints, cv2.COLOR_BGR2RGB)
        # 畫出圓的圓心
        # cv2.circle(color_img, (int(keypoints[0].pt[0]), int(keypoints[0].pt[1])), 5, (0, 255, 0), -1)
        # cv2.imshow("color_img",color_img)
        # cv2.waitKey()
        return keypoints

# 檢測連接配接器圓形位置
def circle_detect(image):
    # 灰階化
    circle_img = image.copy()
    gray = cv2.cvtColor(circle_img, cv2.COLOR_BGR2GRAY)

    img = cv2.medianBlur(gray, 3)

    # 針角圓心坐标
    out_x = 0
    out_y = 0

    # 霍夫變換圓檢測
    circles = cv2.HoughCircles(img, cv2.HOUGH_GRADIENT, 1, 10e10, param1=100, param2=30, minRadius=10, maxRadius=200)
    # 如果沒檢測到會報錯
    # 這種判斷方式過于簡單
    if circles is None:
        print("沒有檢測到連接配接器外圓")
        return False, 0
    else:
        for circle in circles[0]:
            # 圓的基本資訊
            # print(circle[2])
            # 坐标行列－圓心坐标
            out_x = int(circle[0])
            out_y = int(circle[1])
            # 半徑
            r = int(circle[2])
            # # 在原圖用指定顔色标記出圓的邊界
            # cv2.circle(circle_img, (out_x, out_y), r, (0, 0, 255), 2)
            # # # 畫出圓的圓心
            # cv2.circle(circle_img, (out_x, out_y), 3, (0, 0, 255), -1)
            cv2.circle(circle_img, (out_x, out_y), r, (0, 0, 255), 2)
            # # 畫出圓的圓心
            cv2.circle(circle_img, (out_x, out_y), 3, (0, 0, 255), -1)

        # cv2.namedWindow("circle_img", 2)
        # cv2.imshow("circle_img", circle_img)
        # cv2.waitKey()

        # 記錄外圓坐标
        out_xpoint = out_x
        out_ypoint = out_y

        # 隻框出單個針角的位置區域
        step_center = 15
        step_rect = 30
        out_x -= step_center
        out_y -= step_center


        needleRect = image[out_y: out_y + step_rect, out_x: out_x + step_rect]
        # cv2.namedWindow("needleRect", 2)
        # cv2.imshow("needleRect", needleRect)
        # cv2.waitKey()

        # 根據檢測到的圓形連接配接器中心找針角位置
        centerPoint = needelCenter_detect(needleRect)

        if len(centerPoint) == 0:
            print("調整位置")
            return False, 0
        else:
            # 将針角的坐标原還至原圖
            in_x = int(centerPoint[0].pt[0])
            in_y = int(centerPoint[0].pt[1])
            in_x +=  out_x
            in_y +=  out_y

            # 畫出針角的圓心
            cv2.circle(circle_img, (in_x, in_y), 3, (0, 255, 0), -1)

            # 計算兩者的距離
            # 假設通過标定其一個像素代表0.0056mm
            DPI = 0.019696448792778324
            dis = math.sqrt(math.pow(out_xpoint - in_x,2) + math.pow(out_ypoint - in_y,2))*DPI
            # print("兩者互相之間的距離為（mm）:", dis)
            #
            # # 将計算結果儲存在xml檔案
            # configFile_xml = "wellConfig.xml"
            # tree = ET.parse(configFile_xml)
            # root = tree.getroot()
            # secondRoot = root.find("distance")
            # precisionValue = root.find("precision")
            # result = root.find("result")
            #
            # secondRoot.text = str(dis)
            # tree.write("wellConfig.xml")

            # if dis > float(precisionValue.text):
            #     result.text = str("發現插針歪斜")
            #     tree.write("wellConfig.xml", encoding="utf_8")
            #     print("發現插針歪斜")
            # else:
            #     result.text = str("沒有插針歪斜,産品合格！")
            #     tree.write("wellConfig.xml", encoding="utf_8")
            #     print("沒有插針歪斜,産品合格！")

            # cv2.namedWindow("image", 2)
            # cv2.imshow("image",circle_img)
            # cv2.waitKey()
            isExists = os.path.exists("./runs/needle/")
            if not isExists:
                os.makedirs("./runs/needle/")
            cv2.imwrite("./runs/needle/OneNeedleSmall.jpg",circle_img)

            return True, dis


def dect_danZhen_start(needleImagePath, roi_TemplatePath):

    # # 這個需要使用者在圖檔中手動選取ROI
    template = cv2.imread(roi_TemplatePath)
    image = cv2.imread(needleImagePath)

    if template is None or image is None:
        return "圖檔讀取失敗", -1

    theight, twidth = template.shape[:2]
    # 執行模闆比對，采用的比對方式cv2.TM_SQDIFF_NORMED
    result = cv2.matchTemplate(image, template, cv2.TM_CCOEFF_NORMED)
    # 歸一化處理
    cv2.normalize(result, result, 0, 1, cv2.NORM_MINMAX, -1)
    # 尋找矩陣（一維數組當做向量，用Mat定義）中的最大值和最小值的比對結果及其位置
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
    # 比對值轉換為字元串
    # 對于cv2.TM_SQDIFF及cv2.TM_SQDIFF_NORMED方法min_val越趨近與0比對度越好，比對位置取min_loc
    # 對于其他方法max_val越趨近于1比對度越好，比對位置取max_loc
    strmin_val = str(max_val)
    # 繪制矩形邊框，将比對區域标注出來
    # min_loc：矩形定點
    # (min_loc[0]+twidth,min_loc[1]+theight)：矩形的寬高
    # (0,0,225)：矩形的邊框顔色；2：矩形邊框寬度
    # cv2.rectangle(image, max_loc, (max_loc[0] + twidth, max_loc[1] + theight), (0, 0, 225), 2)
    # 顯示結果,并将比對值顯示在标題欄上
    # cv2.namedWindow("MatchResult----MatchingValue=" +  strmin_val, 2)
    # cv2.imshow("MatchResult----MatchingValue=" + strmin_val, image)
    # cv2.waitKey()

    roi = image[max_loc[1]:max_loc[1] + theight, max_loc[0]:max_loc[0] + twidth]
    dect_result = circle_detect( roi)

    if dect_result[0] == True:
        print("檢測成功")
        if dect_result[1] > 0.05:
            print("不合格,距離為",dect_result[1])
            return "不合格",dect_result[1]
        else:
            print("合格,距離為",dect_result[1],"mm")
            return "合格",dect_result[1]
    else:
        print("檢測失敗")
        return "檢測失敗", -1

def dect_danZhen_ceshi(image, template):

    # # 這個需要使用者在圖檔中手動選取ROI
    # template = cv2.imread(roi_TemplatePath)
    # image = cv2.imread(needleImagePath)

    if template is None or image is None:
        return "圖檔讀取失敗", -1

    theight, twidth = template.shape[:2]
    # 執行模闆比對，采用的比對方式cv2.TM_SQDIFF_NORMED
    result = cv2.matchTemplate(image, template, cv2.TM_CCOEFF_NORMED)
    # 歸一化處理
    cv2.normalize(result, result, 0, 1, cv2.NORM_MINMAX, -1)
    # 尋找矩陣（一維數組當做向量，用Mat定義）中的最大值和最小值的比對結果及其位置
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
    # 比對值轉換為字元串
    # 對于cv2.TM_SQDIFF及cv2.TM_SQDIFF_NORMED方法min_val越趨近與0比對度越好，比對位置取min_loc
    # 對于其他方法max_val越趨近于1比對度越好，比對位置取max_loc
    strmin_val = str(max_val)
    # 繪制矩形邊框，将比對區域标注出來
    # min_loc：矩形定點
    # (min_loc[0]+twidth,min_loc[1]+theight)：矩形的寬高
    # (0,0,225)：矩形的邊框顔色；2：矩形邊框寬度
    # cv2.rectangle(image, max_loc, (max_loc[0] + twidth, max_loc[1] + theight), (0, 0, 225), 2)
    # 顯示結果,并将比對值顯示在标題欄上
    # cv2.namedWindow("MatchResult----MatchingValue=" +  strmin_val, 2)
    # cv2.imshow("MatchResult----MatchingValue=" + strmin_val, image)
    # cv2.waitKey()

    roi = image[max_loc[1]:max_loc[1] + theight, max_loc[0]:max_loc[0] + twidth]
    dect_result = circle_detect( roi)

    if dect_result[0] == True:
        print("檢測成功")
        if dect_result[1] > 0.05:
            print("不合格,距離為",dect_result[1])
            return "不合格",dect_result[1]
        else:
            print("合格,距離為",dect_result[1],"mm")
            return "合格",dect_result[1]
    else:
        print("檢測失敗")
        return "檢測失敗", -1

if __name__ == "__main__":
# # 從xml檔案中讀取要檢測的圖檔位置
#     configFile_xml = "wellConfig.xml"
#     tree = ET.parse(configFile_xml)
#     root = tree.getroot()
#     needleImagePath = root.find("needleFilePath")
#     needleTemplate = root.find("needleMatchFilePath")
#
#     result = dect_danZhen_start(needleImagePath.text,needleTemplate.text)
#     print(result)

# 測試
    image = cv2.imread("1031/E_0_6.jpg")
    roi = image[1263:1368, 1954:2050]
    # roi = cv2.imread("Images/oneNeedle/ROI.jpg")
    cv2.imshow("roi",roi)
    cv2.waitKey()
    reslut = dect_danZhen_ceshi(image, roi)
    print(reslut)

    # needleImagePath = "1031/E_0_6.jpg"
    # roi_TemplatePath = "Images/oneNeedle/ROI.jpg"
    # result = dect_danZhen_start(needleImagePath,roi_TemplatePath)
    # print(result)





# # 1 路徑寫入xml檔案
# # 2 檢測結果也寫入xml
# if __name__ == "__main__":
# # # 從xml檔案中讀取要檢測的圖檔位置
#     configFile_xml = "wellConfig.xml"
#     tree = ET.parse(configFile_xml)
#     root = tree.getroot()
#     needleImagePath = root.find("needleFilePath")
#     needleTemplate = root.find("needleMatchFilePath")
#
# #     # 讀檔案
# #     needleImagePath = "Images/Final/E_0_6.jpg"
# #     needleTemplate = "Images/Final/template.jpg"
#     #  檢測有針的
#     image = cv2.imread(needleImagePath.text)
#     # # 這個需要使用者在圖檔中手動選取ROI
#     template = cv2.imread(needleTemplate.text)
#     #  檢測有針的
#     # image = cv2.imread("Images/Final/E_0_6.jpg")
#     # # 這個需要使用者在圖檔中手動選取ROI
#     # template = cv2.imread("Images/Final/template.jpg")
#
#     theight, twidth = template.shape[:2]
#     # 執行模闆比對，采用的比對方式cv2.TM_SQDIFF_NORMED
#     result = cv2.matchTemplate(image, template, cv2.TM_CCOEFF_NORMED)
#     # 歸一化處理
#     cv2.normalize(result, result, 0, 1, cv2.NORM_MINMAX, -1)
#     # 尋找矩陣（一維數組當做向量，用Mat定義）中的最大值和最小值的比對結果及其位置
#     min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
#     # 比對值轉換為字元串
#     # 對于cv2.TM_SQDIFF及cv2.TM_SQDIFF_NORMED方法min_val越趨近與0比對度越好，比對位置取min_loc
#     # 對于其他方法max_val越趨近于1比對度越好，比對位置取max_loc
#     strmin_val = str(max_val)
#     # 繪制矩形邊框，将比對區域标注出來
#     # min_loc：矩形定點
#     # (min_loc[0]+twidth,min_loc[1]+theight)：矩形的寬高
#     # (0,0,225)：矩形的邊框顔色；2：矩形邊框寬度
#     # cv2.rectangle(image, max_loc, (max_loc[0] + twidth, max_loc[1] + theight), (0, 0, 225), 2)
#     # 顯示結果,并将比對值顯示在标題欄上
#     # cv2.namedWindow("MatchResult----MatchingValue=" +  strmin_val, 2)
#     # cv2.imshow("MatchResult----MatchingValue=" + strmin_val, image)
#     # cv2.waitKey()
#
#     roi = image[max_loc[1]:max_loc[1] + theight, max_loc[0]:max_loc[0] + twidth]
#     dect_result = circle_detect( roi)
#
#     if dect_result[0] == True:
#         print("檢測成功")
#         if dect_result[1] > 0.05:
#             print("不合格,距離為",dect_result[1])
#         else:
#             print("合格,距離為",dect_result[1],"mm")
#     else:
#         print("檢測失敗")
#
#
通過模闆比對先定位檢測的對象再檢測圓形零件和孔針03

繼續閱讀

無法解析的外部符号 wmain，該符号在函數 "void cdecl mainCRTStartupHelper(struct HINSTANCE *,unsigned short con......

TestLink導出用例轉換工具(XML2Excel)

YAML簡介和PyYAML安全操作YAML支援的類型YAML的優點：yaml的基本文法python操作

cs231n斯坦福基于卷積神經網絡的CV學習筆記（一）KNN和線性分類器/分類器損失/反向傳播一，KNN圖像分類算法二，線性分類器三，線性分類器損失四，反向傳播五，神經網絡

Small tricks

libsvm for python 安裝

學習軟體測試基礎測試第七天

Zeppelin 配置通路 REST APIApache Zeppelin Configuration REST API

【Torch】最簡潔logging使用指南

27. Remove Element(清單)題目代碼

Cloud Studio初體驗

使用 ctypes 進行 Python 和 C 的混合程式設計

【python】【資料處理】畫多元資料分布圖

【python】netconf協定對接管理裝置

「Python 網絡自動化」NETCONF —— Python 使用 NETCONF 管理配置 H3C 網絡裝置

在python中建立excel并寫入
