python - 如何使用 Python OpenCV 查找表格图像中的行数和列数？

Question

如何通过 OpenCV 获取图像表中的行数和列数。

用于在我正确的表中获取框的代码

contours, hierarchy = cv2.findContours(img_final_bin, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

def sort_contours(cnts, method="left-to-right"):
# initialize the reverse flag and sort index
reverse = False
i = 0
# handle if we need to sort in reverse
if method == "right-to-left" or method == "bottom-to-top":
    reverse = True
# handle if we are sorting against the y-coordinate rather than
# the x-coordinate of the bounding box
if method == "top-to-bottom" or method == "bottom-to-top":
    i = 1
# construct the list of bounding boxes and sort them from top to
# bottom
boundingBoxes = [cv2.boundingRect(c) for c in cnts]
(cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),
    key=lambda b:b[1][i], reverse=reverse))
# return the list of sorted contours and bounding boxes
return (cnts, boundingBoxes)

(contours, boundingBoxes) = sort_contours(contours, method="top-to-bottom")

Answer 1

这里有两种方法:第一种使用表格的结构来确定行数和列数，而第二种使用单元格计数。

方法#1:表结构

这个想法是我们可以计算表格的水平线和垂直线的数量来确定行数和列数。对于行，它是行 = 水平线 - 1；对于列，它是列 = 垂直线 - 1。

检测到的绿色水平线

检测到绿色垂直线

结果

Rows: 7
Columns: 4

代码

import cv2

# Load image, convert to grayscale, Otsu's threshold
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# Find number of rows 
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25,1))
horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
rows = 0
for c in cnts:
    cv2.drawContours(image, [c], -1, (36,255,12), 2)
    rows += 1

# Find number of columns
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,25))
vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
columns = 0
for c in cnts:
    cv2.drawContours(image, [c], -1, (36,255,12), 2)
    columns += 1

print('Rows:', rows - 1)
print('Columns:', columns - 1)

cv2.imshow('thresh', thresh)
cv2.imshow('image', image)
cv2.waitKey()

<小时/>

方法#2:细胞计数

1. 获取二值图像。加载图像，转换为灰度，Gaussian blur ，然后 Otsu's threshold .

2. 删除单元格内的文本。使用 cv2.contourArea() 查找轮廓并进行过滤。通过用 cv2.drawContours() 填充轮廓来删除文本

3. 反转图像。我们反转图像，使单元格为白色，背景为黑色

4. 对单元格进行排序并对行/列求和。我们 find contours然后使用 imutils.contours.sort_contours 从上到下对轮廓进行排序。接下来我们迭代轮廓并找到 centroid获取(cX, cY)坐标。我们的想法是，我们可以比较每个单元格的 cY 值，通过使用偏移量来确定它是新行还是同一行中的单元格。如果cY值是+/-某个偏移值，则单元格应该位于同一行。如果它更大，则意味着该单元格位于新行中。我们构建一个模型表，其中表的长度为您提供行数，而任何索引的长度为您提供列数。

<小时/>

二值图像

删除文本轮廓+倒置图像

这是迭代每个单元格以计算行数和列数的可视化

结果

Rows: 7
Columns: 4

代码

import numpy as np
from imutils import contours
import cv2

# Load image, grayscale, Gaussian blur, Otsu's threshold
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5,5), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# Find contours and remove text inside cells
cnts = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    area = cv2.contourArea(c)
    if area < 4000:
        cv2.drawContours(thresh, [c], -1, 0, -1)

# Invert image
invert = 255 - thresh
offset, old_cY, first = 10, 0, True
visualize = cv2.cvtColor(invert, cv2.COLOR_GRAY2BGR)

# Find contours, sort from top-to-bottom and then sum up column/rows
cnts = cv2.findContours(invert, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
(cnts, _) = contours.sort_contours(cnts, method="top-to-bottom")
for c in cnts:
    # Find centroid
    M = cv2.moments(c)
    cX = int(M["m10"] / M["m00"])
    cY = int(M["m01"] / M["m00"])
    
    # New row
    if (abs(cY) - abs(old_cY)) > offset:
        if first:
            row, table = [], []
            first = False
        old_cY = cY
        table.append(row)
        row = []
    
    # Cell in same row
    if ((abs(cY) - abs(old_cY)) <= offset) or first:
        row.append(1)
   
    # Uncomment to visualize 
    '''
    cv2.circle(visualize, (cX, cY), 10, (36, 255, 12), -1) 
    cv2.imshow('visualize', visualize)
    cv2.waitKey(200)
    '''

print('Rows: {}'.format(len(table)))
print('Columns: {}'.format(len(table[1])))

cv2.imshow('invert', invert)
cv2.imshow('thresh', thresh)
cv2.waitKey()