Python OpenCV findcontours（）无法检测轮廓

我正试图从下面的图像中读取中的数字。

我使用OpenCV中的模板匹配来查找与图像对应的数字。因此，中的问题分为三个步骤：
第1步：检测MICR E-13B字体，使用FindOntours（）和检测矩形即可轻松完成。实现以下输出。

第2步：在第2步中，我们从上面获取每个轮廓（包含MICR E-13B字体），以便将它们分开，以便进一步单独断开数字。
步骤3:

这就是错误发生的地方。

获得上述输出后，现在的任务是将数字组分解为单个数字，以便使用OpenCV中的模板匹配来匹配它们。但当我应用findcontour方法并继续为每个轮廓检测boundRect时，我没有得到任何边界矩形。
以下是各个步骤的代码：
步骤1:

# apply a tophat (whitehat) morphological operator to find light
# regions against a dark background
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel)

# compute the Scharr gradient of the tophat image, then scale
# the rest back into the range [0, 255]
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0,
    ksize=-1)
gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
gradX = gradX.astype("uint8")

# apply a closing operation using the rectangular kernel to help
# cloes gaps in between credit card number digits, then apply
# Otsu's thresholding method to binarize the image
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
thresh = cv2.threshold(gradX, 0, 255,
    cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

# apply a second closing operation to the binary image, again
# to help close gaps between credit card number regions
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel)

thresh = cv2.dilate(thresh, None, iterations = 3)
clone = np.dstack([thresh.copy()] * 3
# find contours in the thresholded image, then initialize the
# list of digit locations
cnts = cv2.findContours(thresh.copy(), cv2.RETR_TREE,
    cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
locs = []

# loop over the contours
for (i, c) in enumerate(cnts):
    (x, y, w, h) = cv2.boundingRect(c)
    if i<=3:   #First 4 images are the MICR font
        cv2.rectangle(clone, (x,y), (x+w, y+h), (255,0,0), 1) #color is set to blue but it shows white (error?)
        locs.append((x, y, w, h))

locs = sorted(locs, key=lambda x:x[0])
output = []
print (locs)

for (i, (gX, gY, gW, gH)) in enumerate(locs):
    if i==0:
        group = gray[gY:gY+gH, gX:gX+gW]
        cv2.rectangle(gray, (gX, gY), (gX+gW, gY+gH), (255,0,0), 1)
        group = cv2.threshold(group, 0, 255,
            cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

         # re-initialize the clone image so we can draw on it again
         clone = np.dstack([group.copy()]*3)
         cv2.rectangle(clone, (gX, gY), (gX+gW, gY+gH), (255,0,0), 1)
         cv2.imshow('Image5', clone)
         cv2.waitKey()

# detect the contours of each individual digit in the group,
# then sort the digit contours from left to right
digitCnts = cv2.findContours(group.copy(), cv2.RETR_TREE,
        cv2.CHAIN_APPROX_SIMPLE)
digitCnts = digitCnts[0] if imutils.is_cv2() else digitCnts[1]
cv2.drawContours(clone, digitCnts, -1, (0,255,0), 1)
cv2.imshow('Image6', clone)
cv2.waitKey()
for c in digitCnts:
    # compute the bounding box of the individual digit, extract
    # the digit, and resize it to have the same fixed size as
    # the reference MICR images
    (x, y, w, h) = cv2.boundingRect(c)
    print (x, y, x+w, y+h)
    cv2.rectangle(clone, (x,y), (x+w, y+h), (255,0,0), 3)
    cv2.imshow('Image7', clone) 
    cv2.waitKey()

错误输出：绿色遮罩未正确绑定矩形。

第三步：

# apply a tophat (whitehat) morphological operator to find light
# regions against a dark background
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel)

# compute the Scharr gradient of the tophat image, then scale
# the rest back into the range [0, 255]
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0,
    ksize=-1)
gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
gradX = gradX.astype("uint8")

# apply a closing operation using the rectangular kernel to help
# cloes gaps in between credit card number digits, then apply
# Otsu's thresholding method to binarize the image
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
thresh = cv2.threshold(gradX, 0, 255,
    cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

# apply a second closing operation to the binary image, again
# to help close gaps between credit card number regions
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel)

thresh = cv2.dilate(thresh, None, iterations = 3)
clone = np.dstack([thresh.copy()] * 3
# find contours in the thresholded image, then initialize the
# list of digit locations
cnts = cv2.findContours(thresh.copy(), cv2.RETR_TREE,
    cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
locs = []

# loop over the contours
for (i, c) in enumerate(cnts):
    (x, y, w, h) = cv2.boundingRect(c)
    if i<=3:   #First 4 images are the MICR font
        cv2.rectangle(clone, (x,y), (x+w, y+h), (255,0,0), 1) #color is set to blue but it shows white (error?)
        locs.append((x, y, w, h))

locs = sorted(locs, key=lambda x:x[0])
output = []
print (locs)

for (i, (gX, gY, gW, gH)) in enumerate(locs):
    if i==0:
        group = gray[gY:gY+gH, gX:gX+gW]
        cv2.rectangle(gray, (gX, gY), (gX+gW, gY+gH), (255,0,0), 1)
        group = cv2.threshold(group, 0, 255,
            cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

         # re-initialize the clone image so we can draw on it again
         clone = np.dstack([group.copy()]*3)
         cv2.rectangle(clone, (gX, gY), (gX+gW, gY+gH), (255,0,0), 1)
         cv2.imshow('Image5', clone)
         cv2.waitKey()

# detect the contours of each individual digit in the group,
# then sort the digit contours from left to right
digitCnts = cv2.findContours(group.copy(), cv2.RETR_TREE,
        cv2.CHAIN_APPROX_SIMPLE)
digitCnts = digitCnts[0] if imutils.is_cv2() else digitCnts[1]
cv2.drawContours(clone, digitCnts, -1, (0,255,0), 1)
cv2.imshow('Image6', clone)
cv2.waitKey()
for c in digitCnts:
    # compute the bounding box of the individual digit, extract
    # the digit, and resize it to have the same fixed size as
    # the reference MICR images
    (x, y, w, h) = cv2.boundingRect(c)
    print (x, y, x+w, y+h)
    cv2.rectangle(clone, (x,y), (x+w, y+h), (255,0,0), 3)
    cv2.imshow('Image7', clone) 
    cv2.waitKey()

错误输出：

---

这就是产生错误的地方，因为应该将步骤2的输出分割为单独的数字，如“9”、“5”等，这些数字可以传递到模板匹配。但等高线的长度为11，并且在上一步的输出中没有绘制边界框来表示单独的数字。

前景应为白色，背景应为黑色。调用

findContours

之前，反转图像（

255-image

）。此外，图像应该只有黑白，但我看到一些灰色区域。一定要创建一个二进制掩码@Miki，我编辑了代码和图像，使前景为白色，背景为黑色。但是，检测所有MICR数字并应用

findContours

后的输出会产生错误

绿色掩码

，并且使用上述轮廓进一步分离数字的

红色掩码

也会产生错误。