我正在尝试获取图像中表格的水平和垂直线,以提取单元格中的文本。这是我使用的图片:
我使用下面的代码提取垂直和水平线:
img = cv2.imread(img_for_box_extraction_path, 0) # Read the image
(thresh, img_bin) = cv2.threshold(img, 200, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU) # Thresholding the image
img_bin = 255-img_bin # Invert the image
cv2.imwrite("Image_bin_2.jpg",img_bin)
# Defining a kernel length
kernel_length = np.array(img).shape[1]//140
# A verticle kernel of (1 X kernel_length), which will detect all the verticle lines from the image.
verticle_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, kernel_length))
# A horizontal kernel of (kernel_length X 1), which will help to detect all the horizontal line from the image.
hori_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (kernel_length, 1))
# A kernel of (3 X 3) ones.
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
# Morphological operation to detect verticle lines from an image
img_temp1 = cv2.erode(img_bin, verticle_kernel, iterations=3)
verticle_lines_img = cv2.dilate(img_temp1, verticle_kernel, iterations=3)
cv2.imwrite("verticle_lines_2.jpg",verticle_lines_img)
# Morphological operation to detect horizontal lines from an image
img_temp2 = cv2.erode(img_bin, hori_kernel, iterations=3)
horizontal_lines_img = cv2.dilate(img_temp2, hori_kernel, iterations=3)
cv2.imwrite("horizontal_lines_2.jpg",horizontal_lines_img)
我使用下面的代码将两个图像加在一起
# Weighting parameters, this will decide the quantity of an image to be added to make a new image.
alpha = 0.5
beta = 1.0 - alpha
# This function helps to add two image with specific weight parameter to get a third image as summation of two image.
img_final_bin = cv2.addWeighted(verticle_lines_img, alpha, horizontal_lines_img, beta, 0.0)
img_final_bin = cv2.erode(~img_final_bin, kernel, iterations=2)
(thresh, img_final_bin) = cv2.threshold(img_final_bin, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
# For Debugging
# Enable this line to see verticle and horizontal lines in the image which is used to find boxes
cv2.imwrite("img_final_bin_2.jpg",img_final_bin)
对于您的第一个二进制图像,沿水平方向使用CV_REDUCE_AVG标志尝试reduce,然后对第二个二进制图像沿垂直方向进行尝试。您将获得Threshols直方图。并使用它们来过滤行。
作为替代方案,您可以尝试使用霍夫线检测器和按长度和斜度过滤线。
这是一个简单的方法:
二进制图像
水平检测
垂直检测
组合式口罩
以绿色删除的行
结果
import cv2
import numpy as np
# Load image, grayscale, Gaussian blur, Otsu's threshold
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Detect horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (50,1))
horizontal_mask = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=1)
# Detect vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,50))
vertical_mask = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=1)
# Combine masks and remove lines
table_mask = cv2.bitwise_or(horizontal_mask, vertical_mask)
image[np.where(table_mask==255)] = [255,255,255]
cv2.imshow('thresh', thresh)
cv2.imshow('horizontal_mask', horizontal_mask)
cv2.imshow('vertical_mask', vertical_mask)
cv2.imshow('table_mask', table_mask)
cv2.imshow('image', image)
cv2.waitKey()