python - 使用 OpenCV 检测表格图像中的行数和列数

Question

我们如何通过 Opencv 获取 Image 表中的行数和列数。

获取表格中我正确的框的代码

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")

标签： pythonimageopencvimage-processingcomputer-vision

Answer 1

这是一种潜在的方法：

1. 获取二值图像。加载图像，转换为灰度，高斯模糊，然后是 Otsu 的阈值。

2. 删除单元格内的文本。查找轮廓并使用过滤器cv2.contourArea()通过填充轮廓来删除文本cv2.drawContours()

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。我们找到轮廓top-to-bottom，然后使用对轮廓进行排序imutils.contours.sort_contours。接下来我们遍历轮廓并找到质心以获得(cX, cY)坐标。这个想法是我们可以cY通过使用偏移量来比较每个单元格的值，以确定它是新行还是同一行中的单元格。cY如果值为 +/- 某个偏移值，则单元格应位于同一行中。如果它更大，则表示该单元格位于新行中。我们构建了一个模型表，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。

---

二进制图像

去除文字轮廓+倒置图像

这是遍历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()