python - 使用 OpenCV 和 Python 从图像中识别和裁剪文本的问题

Question

我正在使用取自以下答案的代码:Detect text region in image using Opencv

我正在使用的代码是:

import cv2
def captch_ex(file_name ):
    img  = cv2.imread(file_name)

    img_final = cv2.imread(file_name)
    img2gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    ret, mask = cv2.threshold(img2gray, 180, 255, cv2.THRESH_BINARY)
    image_final = cv2.bitwise_and(img2gray , img2gray , mask =  mask)
    ret, new_img = cv2.threshold(image_final, 180 , 255, cv2.THRESH_BINARY)  # for black text , cv.THRESH_BINARY_INV
    '''
            line  8 to 12  : Remove noisy portion
    '''
    kernel = cv2.getStructuringElement(cv2.MORPH_CROSS,(3 , 3)) # to manipulate the orientation of dilution , large x means horizonatally dilating  more, large y means vertically dilating more
    dilated = cv2.dilate(new_img,kernel,iterations = 9) # dilate , more the iteration more the dilation

    contours = cv2.findContours(dilated,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)[0] # get contours
    index = 0
    for contour in contours:
        # get rectangle bounding contour
        [x,y,w,h] = cv2.boundingRect(contour)

        #Don't plot small false positives that aren't text
        if w < 35 and h<35:
            continue

        # draw rectangle around contour on original image
        cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,255),2)

        #you can crop image and send to OCR  , false detected will return no text :)
        cropped = img_final[y :y +  h , x : x + w]

        s = file_name + 'crop_' + str(index) + '.png'
        cv2.imwrite(s , cropped)
        index = index + 1
    # write original image with added contours to disk

file_name ='rec_5.png'
captch_ex(file_name)

需要指出的最大区别如下: contours = cv2.findContours(dilated,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)[0] [0]被添加是因为没有它我一直收到这个错误

Traceback (most recent call last):
  File "test2.py", line 38, in <module>
    captch_ex(file_name)
  File "test2.py", line 20, in captch_ex
    [x,y,w,h] = cv2.boundingRect(contour)
TypeError: points is not a numpy array, neither a scalar

不幸的是，我找不到源代码，但我在某处读到版本 3 的这种方法发生了变化，现在这是必需的。

我的问题是，当我为这个函数提供图像时，我会收到数百个 1 px.宽度裁剪的图像，不能完成引用答案中明显解决的功能。

截至目前，我猜测额外的 [0]上面提到的可能是错误的原因，但没有它我可以让脚本完成。

Answer 1

问题在于 cv2.findContours()方法，实际上它对于 Opencv 2 和 Opencv 3 有不同的返回参数，您必须检查您正在使用的 Opencv 版本的文档，一般来说:

对于Opencv 2 :

contours, hierarchy = cv2.findContours(dilated,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)

对于 Opencv 3 :

image, contours, hierarchy = cv2.findContours(dilated,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)

现在你不需要 [0]破解访问轮廓，您可以进一步继续:

for contour in contours:
    # get rectangle bounding contour
    [x,y,w,h] = cv2.boundingRect(contour)