处理 table 的图像以从中获取数据
Processing an image of a table to get data from it
我有这张 table 的图片（如下所示）。我正在尝试从 table 获取数据，类似于此表单（table 图片的第一行）：
rows[0] = [x,x, , , , ,x, ,x,x, ,x, ,x, , , , ,x, , , ,x,x,x, ,x, ,x, , , , ]
我需要 x 的数量以及空格的数量。
还会有其他 table 个与此相似的图像（都有 x 和相同的列数）。
到目前为止，我能够使用 x 的图像检测所有 x。而且我可以在某种程度上检测到线条。我正在为 python 使用 open cv2。我还使用 houghTransform 来检测水平线和垂直线（效果非常好）。
我正在尝试弄清楚如何逐行并将信息存储在列表中。
这些是训练图像：
用于检测x（代码中的train1.png）
用于检测线条（代码中train2.png）
用于检测线条（代码中train3.png）
这是我目前的代码：
# process images
from pytesser import *
from PIL import Image
from matplotlib import pyplot as plt
import pytesseract
import numpy as np
import cv2
import math
import os
# the table images
images = ['table1.png', 'table2.png', 'table3.png', 'table4.png', 'table5.png']
# the template images used for training
templates = ['train1.png', 'train2.png', 'train3.png']
def hough_transform(im):
img = cv2.imread('imgs/'+im)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 50, 150, apertureSize=3)
lines = cv2.HoughLines(edges, 1, np.pi/180, 200)
i = 1
for rho, theta in lines[0]:
a = np.cos(theta)
b = np.sin(theta)
x0 = a*rho
y0 = b*rho
x1 = int(x0 + 1000*(-b))
y1 = int(y0 + 1000*(a))
x2 = int(x0 - 1000*(-b))
y2 = int(y0 - 1000*(a))
#print '%s - 0:(%s,%s) 1:(%s,%s), 2:(%s,%s)' % (i,x0,y0,x1,y1,x2,y2)
cv2.line(img, (x1,y1), (x2,y2), (0,0,255), 2)
i += 1
fn = os.path.splitext(im)[0]+'-lines'
cv2.imwrite('imgs/'+fn+'.png', img)
def match_exes(im, te):
img_rgb = cv2.imread('imgs/'+im)
img_gry = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)
template = cv2.imread('imgs/'+te, 0)
w, h = template.shape[::-1]
res = cv2.matchTemplate(img_gry, template, cv2.TM_CCOEFF_NORMED)
threshold = 0.71
loc = np.where(res >= threshold)
pts = []
exes = []
blanks = []
for pt in zip(*loc[::-1]):
pts.append(pt)
cv2.rectangle(img_rgb, pt, (pt[0]+w, pt[1]+h), (0,0,255), 1)
fn = os.path.splitext(im)[0]+'-exes'
cv2.imwrite('imgs/'+fn+'.png', img_rgb)
return pts, exes, blanks
def match_horizontal_lines(im, te, te2):
img_rgb = cv2.imread('imgs/'+im)
img_gry = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)
template = cv2.imread('imgs/'+te, 0)
w1, h1 = template.shape[::-1]
template2 = cv2.imread('imgs/'+te2, 0)
w2, h2 = template2.shape[::-1]
# first line template (the downward facing line)
res1 = cv2.matchTemplate(img_gry, template, cv2.TM_CCOEFF_NORMED)
threshold1 = 0.8
loc1 = np.where(res1 >= threshold1)
# second line template (the upward facing line)
res2 = cv2.matchTemplate(img_gry, template2, cv2.TM_CCOEFF_NORMED)
threshold2 = 0.8
loc2 = np.where(res2 >= threshold2)
pts = []
exes = []
blanks = []
# find first line template (the downward facing line)
for pt in zip(*loc1[::-1]):
pts.append(pt)
cv2.rectangle(img_rgb, pt, (pt[0]+w1, pt[1]+h1), (0,0,255), 1)
# find second line template (the upward facing line)
for pt in zip(*loc2[::-1]):
pts.append(pt)
cv2.rectangle(img_rgb, pt, (pt[0]+w2, pt[0]+h2), (0,0,255), 1)
fn = os.path.splitext(im)[0]+'-horiz'
cv2.imwrite('imgs/'+fn+'.png', img_rgb)
return pts, exes, blanks
# process
text = ''
for img in images:
print 'processing %s' % img
hough_transform(img)
pts, exes, blanks = match_exes(img, templates[0])
pts1, exes1, blanks1 = match_horizontal_lines(img, templates[1], templates[2])
text += '%s: %s x\'s & %s horizontal lines\n' % (img, len(pts), len(pts1))
# statistics file
outputFile = open('counts.txt', 'w')
outputFile.write(text)
outputFile.close()
并且，输出图像看起来像这样（如您所见，检测到所有 x 但不是所有行）
x的
水平线
霍夫变换
正如我所说，我实际上只是想从 table 中获取数据，类似于这种形式（table 图片的第一行）：
row a = [x,x, , , , ,x, ,x,x, ,x, ,x, , , , ,x, , , ,x,x,x, ,x, ,x, , , , ]
我需要 x 的数量以及空格的数量。
还会有其他 table 个图像与此图像相似（所有图像都具有 x 和相同的列数和不同的行数）。
此外，我正在使用 python 2.7
好的，我已经弄明白了。我使用了@beaker 提供的在网格线之间查看的建议。
在这样做之前，我必须从 hough 转换代码中删除重复的行。然后，我将那些剩余的行分类为垂直和水平的 2 个列表。从那里，我可以循环遍历水平和垂直，然后创建感兴趣区域 (roi) 图像。每个 roi 图像代表 table 主图像中的一个 'cell'。我检查了每个单元格的轮廓，并注意到当单元格中有 'x' 时，len(contours) >= 2。所以，任何 len(contours) < 2 都是空白 space （我做了几个测试程序来弄清楚这一点）。这是我用来让它工作的代码：
import cv2
import numpy as np
import os
# the list of images (tables)
images = ['table1.png', 'table2.png', 'table3.png', 'table4.png', 'table5.png']
# the list of templates (used for template matching)
templates = ['train1.png']
def remove_duplicates(lines):
# remove duplicate lines (lines within 10 pixels of eachother)
for x1, y1, x2, y2 in lines:
for index, (x3, y3, x4, y4) in enumerate(lines):
if y1 == y2 and y3 == y4:
diff = abs(y1-y3)
elif x1 == x2 and x3 == x4:
diff = abs(x1-x3)
else:
diff = 0
if diff < 10 and diff is not 0:
del lines[index]
return lines
def sort_line_list(lines):
# sort lines into horizontal and vertical
vertical = []
horizontal = []
for line in lines:
if line[0] == line[2]:
vertical.append(line)
elif line[1] == line[3]:
horizontal.append(line)
vertical.sort()
horizontal.sort(key=lambda x: x[1])
return horizontal, vertical
def hough_transform_p(image, template, tableCnt):
# open and process images
img = cv2.imread('imgs/'+image)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 50, 150, apertureSize=3)
# probabilistic hough transform
lines = cv2.HoughLinesP(edges, 1, np.pi/180, 200, minLineLength=20, maxLineGap=999)[0].tolist()
# remove duplicates
lines = remove_duplicates(lines)
# draw image
for x1, y1, x2, y2 in lines:
cv2.line(img, (x1, y1), (x2, y2), (0, 0, 255), 1)
# sort lines into vertical & horizontal lists
horizontal, vertical = sort_line_list(lines)
# go through each horizontal line (aka row)
rows = []
for i, h in enumerate(horizontal):
if i < len(horizontal)-1:
row = []
for j, v in enumerate(vertical):
if i < len(horizontal)-1 and j < len(vertical)-1:
# every cell before last cell
# get width & height
width = horizontal[i+1][1] - h[1]
height = vertical[j+1][0] - v[0]
else:
# last cell, width = cell start to end of image
# get width & height
width = tW
height = tH
tW = width
tH = height
# get roi (region of interest) to find an x
roi = img[h[1]:h[1]+width, v[0]:v[0]+height]
# save image (for testing)
dir = 'imgs/table%s' % (tableCnt+1)
if not os.path.exists(dir):
os.makedirs(dir)
fn = '%s/roi_r%s-c%s.png' % (dir, i, j)
cv2.imwrite(fn, roi)
# if roi contains an x, add x to array, else add _
roi_gry = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(roi_gry, 127, 255, 0)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
if len(contours) > 1:
# there is an x for 2 or more contours
row.append('x')
else:
# there is no x when len(contours) is <= 1
row.append('_')
row.pop()
rows.append(row)
# save image (for testing)
fn = os.path.splitext(image)[0] + '-hough_p.png'
cv2.imwrite('imgs/'+fn, img)
def process():
for i, img in enumerate(images):
# perform probabilistic hough transform on each image
hough_transform_p(img, templates[0], i)
if __name__ == '__main__':
process()
因此，示例图片：
并且，输出（为简洁起见删除了生成文本文件的代码）：
如您所见，文本文件在与图像相同的位置包含相同数量的 x。现在困难的部分已经过去了，我可以继续我的任务了！
我有这张 table 的图片（如下所示）。我正在尝试从 table 获取数据，类似于此表单（table 图片的第一行）：
rows[0] = [x,x, , , , ,x, ,x,x, ,x, ,x, , , , ,x, , , ,x,x,x, ,x, ,x, , , , ]
我需要 x 的数量以及空格的数量。 还会有其他 table 个与此相似的图像（都有 x 和相同的列数）。
到目前为止，我能够使用 x 的图像检测所有 x。而且我可以在某种程度上检测到线条。我正在为 python 使用 open cv2。我还使用 houghTransform 来检测水平线和垂直线（效果非常好）。
我正在尝试弄清楚如何逐行并将信息存储在列表中。
这些是训练图像：
用于检测x（代码中的train1.png）
用于检测线条（代码中train2.png）
用于检测线条（代码中train3.png）
这是我目前的代码：
# process images
from pytesser import *
from PIL import Image
from matplotlib import pyplot as plt
import pytesseract
import numpy as np
import cv2
import math
import os
# the table images
images = ['table1.png', 'table2.png', 'table3.png', 'table4.png', 'table5.png']
# the template images used for training
templates = ['train1.png', 'train2.png', 'train3.png']
def hough_transform(im):
img = cv2.imread('imgs/'+im)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 50, 150, apertureSize=3)
lines = cv2.HoughLines(edges, 1, np.pi/180, 200)
i = 1
for rho, theta in lines[0]:
a = np.cos(theta)
b = np.sin(theta)
x0 = a*rho
y0 = b*rho
x1 = int(x0 + 1000*(-b))
y1 = int(y0 + 1000*(a))
x2 = int(x0 - 1000*(-b))
y2 = int(y0 - 1000*(a))
#print '%s - 0:(%s,%s) 1:(%s,%s), 2:(%s,%s)' % (i,x0,y0,x1,y1,x2,y2)
cv2.line(img, (x1,y1), (x2,y2), (0,0,255), 2)
i += 1
fn = os.path.splitext(im)[0]+'-lines'
cv2.imwrite('imgs/'+fn+'.png', img)
def match_exes(im, te):
img_rgb = cv2.imread('imgs/'+im)
img_gry = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)
template = cv2.imread('imgs/'+te, 0)
w, h = template.shape[::-1]
res = cv2.matchTemplate(img_gry, template, cv2.TM_CCOEFF_NORMED)
threshold = 0.71
loc = np.where(res >= threshold)
pts = []
exes = []
blanks = []
for pt in zip(*loc[::-1]):
pts.append(pt)
cv2.rectangle(img_rgb, pt, (pt[0]+w, pt[1]+h), (0,0,255), 1)
fn = os.path.splitext(im)[0]+'-exes'
cv2.imwrite('imgs/'+fn+'.png', img_rgb)
return pts, exes, blanks
def match_horizontal_lines(im, te, te2):
img_rgb = cv2.imread('imgs/'+im)
img_gry = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)
template = cv2.imread('imgs/'+te, 0)
w1, h1 = template.shape[::-1]
template2 = cv2.imread('imgs/'+te2, 0)
w2, h2 = template2.shape[::-1]
# first line template (the downward facing line)
res1 = cv2.matchTemplate(img_gry, template, cv2.TM_CCOEFF_NORMED)
threshold1 = 0.8
loc1 = np.where(res1 >= threshold1)
# second line template (the upward facing line)
res2 = cv2.matchTemplate(img_gry, template2, cv2.TM_CCOEFF_NORMED)
threshold2 = 0.8
loc2 = np.where(res2 >= threshold2)
pts = []
exes = []
blanks = []
# find first line template (the downward facing line)
for pt in zip(*loc1[::-1]):
pts.append(pt)
cv2.rectangle(img_rgb, pt, (pt[0]+w1, pt[1]+h1), (0,0,255), 1)
# find second line template (the upward facing line)
for pt in zip(*loc2[::-1]):
pts.append(pt)
cv2.rectangle(img_rgb, pt, (pt[0]+w2, pt[0]+h2), (0,0,255), 1)
fn = os.path.splitext(im)[0]+'-horiz'
cv2.imwrite('imgs/'+fn+'.png', img_rgb)
return pts, exes, blanks
# process
text = ''
for img in images:
print 'processing %s' % img
hough_transform(img)
pts, exes, blanks = match_exes(img, templates[0])
pts1, exes1, blanks1 = match_horizontal_lines(img, templates[1], templates[2])
text += '%s: %s x\'s & %s horizontal lines\n' % (img, len(pts), len(pts1))
# statistics file
outputFile = open('counts.txt', 'w')
outputFile.write(text)
outputFile.close()
并且，输出图像看起来像这样（如您所见，检测到所有 x 但不是所有行）
x的
水平线
霍夫变换
正如我所说，我实际上只是想从 table 中获取数据，类似于这种形式（table 图片的第一行）：
row a = [x,x, , , , ,x, ,x,x, ,x, ,x, , , , ,x, , , ,x,x,x, ,x, ,x, , , , ]
我需要 x 的数量以及空格的数量。 还会有其他 table 个图像与此图像相似（所有图像都具有 x 和相同的列数和不同的行数）。
此外，我正在使用 python 2.7
好的，我已经弄明白了。我使用了@beaker 提供的在网格线之间查看的建议。
在这样做之前，我必须从 hough 转换代码中删除重复的行。然后，我将那些剩余的行分类为垂直和水平的 2 个列表。从那里，我可以循环遍历水平和垂直，然后创建感兴趣区域 (roi) 图像。每个 roi 图像代表 table 主图像中的一个 'cell'。我检查了每个单元格的轮廓，并注意到当单元格中有 'x' 时，len(contours) >= 2。所以，任何 len(contours) < 2 都是空白 space （我做了几个测试程序来弄清楚这一点）。这是我用来让它工作的代码：
import cv2
import numpy as np
import os
# the list of images (tables)
images = ['table1.png', 'table2.png', 'table3.png', 'table4.png', 'table5.png']
# the list of templates (used for template matching)
templates = ['train1.png']
def remove_duplicates(lines):
# remove duplicate lines (lines within 10 pixels of eachother)
for x1, y1, x2, y2 in lines:
for index, (x3, y3, x4, y4) in enumerate(lines):
if y1 == y2 and y3 == y4:
diff = abs(y1-y3)
elif x1 == x2 and x3 == x4:
diff = abs(x1-x3)
else:
diff = 0
if diff < 10 and diff is not 0:
del lines[index]
return lines
def sort_line_list(lines):
# sort lines into horizontal and vertical
vertical = []
horizontal = []
for line in lines:
if line[0] == line[2]:
vertical.append(line)
elif line[1] == line[3]:
horizontal.append(line)
vertical.sort()
horizontal.sort(key=lambda x: x[1])
return horizontal, vertical
def hough_transform_p(image, template, tableCnt):
# open and process images
img = cv2.imread('imgs/'+image)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 50, 150, apertureSize=3)
# probabilistic hough transform
lines = cv2.HoughLinesP(edges, 1, np.pi/180, 200, minLineLength=20, maxLineGap=999)[0].tolist()
# remove duplicates
lines = remove_duplicates(lines)
# draw image
for x1, y1, x2, y2 in lines:
cv2.line(img, (x1, y1), (x2, y2), (0, 0, 255), 1)
# sort lines into vertical & horizontal lists
horizontal, vertical = sort_line_list(lines)
# go through each horizontal line (aka row)
rows = []
for i, h in enumerate(horizontal):
if i < len(horizontal)-1:
row = []
for j, v in enumerate(vertical):
if i < len(horizontal)-1 and j < len(vertical)-1:
# every cell before last cell
# get width & height
width = horizontal[i+1][1] - h[1]
height = vertical[j+1][0] - v[0]
else:
# last cell, width = cell start to end of image
# get width & height
width = tW
height = tH
tW = width
tH = height
# get roi (region of interest) to find an x
roi = img[h[1]:h[1]+width, v[0]:v[0]+height]
# save image (for testing)
dir = 'imgs/table%s' % (tableCnt+1)
if not os.path.exists(dir):
os.makedirs(dir)
fn = '%s/roi_r%s-c%s.png' % (dir, i, j)
cv2.imwrite(fn, roi)
# if roi contains an x, add x to array, else add _
roi_gry = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(roi_gry, 127, 255, 0)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
if len(contours) > 1:
# there is an x for 2 or more contours
row.append('x')
else:
# there is no x when len(contours) is <= 1
row.append('_')
row.pop()
rows.append(row)
# save image (for testing)
fn = os.path.splitext(image)[0] + '-hough_p.png'
cv2.imwrite('imgs/'+fn, img)
def process():
for i, img in enumerate(images):
# perform probabilistic hough transform on each image
hough_transform_p(img, templates[0], i)
if __name__ == '__main__':
process()
因此，示例图片：
并且，输出（为简洁起见删除了生成文本文件的代码）：
如您所见，文本文件在与图像相同的位置包含相同数量的 x。现在困难的部分已经过去了，我可以继续我的任务了！