小编fis*_*ill的帖子

我正在尝试从这样的几页中裁剪两列，以便以后进行 OCR，查看沿垂直线分割页面

到目前为止我所得到的是找到标题，以便可以将其裁剪掉：

image = cv2.imread('014-page1.jpg')
im_h, im_w, im_d = image.shape
base_image = image.copy()

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7,7), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# Create rectangular structuring element and dilate
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (50,10))
dilate = cv2.dilate(thresh, kernel, iterations=1)

# Find contours and draw rectangle
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=lambda x: cv2.boundingRect(x)[1])
for c in cnts:
    x,y,w,h = cv2.boundingRect(c) …