从表格图像中提取单个字段以使用 OCR 进行 Excel

Extract individual field from table image to excel with OCR(从表格图像中提取单个字段以使用 OCR 进行 Excel)
本文介绍了从表格图像中提取单个字段以使用 OCR 进行 Excel的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着跟版网的小编来一起学习吧!

问题描述

我已经扫描了具有如下图所示表格的图像:

I have scanned images which have tables as shown in this image:

我正在尝试分别提取每个框并执行 OCR,但是当我尝试检测水平线和垂直线然后检测框时,它会返回以下图像:

I am trying to extract each box separately and perform OCR but when I try to detect horizontal and vertical lines and then detect boxes it's returning the following image:

当我尝试执行其他转换来检测文本(腐蚀和扩张)时,仍然会出现一些剩余的线条,如下所示:

And when I try to perform other transformations to detect text (erode and dilate) some remains of lines are still coming along with text like below:

我无法检测到仅用于执行 OCR 的文本,并且未生成正确的边界框,如下所示:

I cannot detect text only to perform OCR and proper bounding boxes aren't being generated like below:

我无法使用实线得到清晰分隔的框,我已经在一个用paint(如下所示)编辑的图像上尝试了这个以添加数字并且它有效.

I cannot get clearly separated boxes using real lines, I've tried this on an image that was edited in paint(as shown below) to add digits and it works.

我不知道我做错了哪一部分,但如果有什么我应该尝试或更改/添加我的问题,请告诉我.

I don't know which part I'm doing wrong but if there's anything I should try or maybe change/add in my question please please tell me.

#Loading all required libraries 
%pylab inline
import cv2
import numpy as np 
import pandas as pd
import pytesseract
import matplotlib.pyplot as plt
import statistics
from time import sleep
import random

img = cv2.imread('images/scan1.jpg',0)

# for adding border to an image
img1= cv2.copyMakeBorder(img,50,50,50,50,cv2.BORDER_CONSTANT,value=[255,255])

# Thresholding the image
(thresh, th3) = cv2.threshold(img1, 255, 255,cv2.THRESH_BINARY|cv2.THRESH_OTSU)

# to flip image pixel values
th3 = 255-th3

# initialize kernels for table boundaries detections
if(th3.shape[0]<1000):
    ver = np.array([[1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1]])
    hor = np.array([[1,1,1,1,1,1]])

else:
    ver = np.array([[1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1],
               [1]])
    hor = np.array([[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]])




# to detect vertical lines of table borders
img_temp1 = cv2.erode(th3, ver, iterations=3)
verticle_lines_img = cv2.dilate(img_temp1, ver, iterations=3)

# to detect horizontal lines of table borders
img_hor = cv2.erode(th3, hor, iterations=3)
hor_lines_img = cv2.dilate(img_hor, hor, iterations=4)

# adding horizontal and vertical lines
hor_ver = cv2.add(hor_lines_img,verticle_lines_img)

hor_ver = 255-hor_ver

# subtracting table borders from image
temp = cv2.subtract(th3,hor_ver)

temp = 255-temp

#Doing xor operation for erasing table boundaries
tt = cv2.bitwise_xor(img1,temp)

iii = cv2.bitwise_not(tt)

tt1=iii.copy()

#kernel initialization
ver1 = np.array([[1,1],
               [1,1],
               [1,1],
               [1,1],
               [1,1],
               [1,1],
               [1,1],
               [1,1],
               [1,1]])
hor1 = np.array([[1,1,1,1,1,1,1,1,1,1],
               [1,1,1,1,1,1,1,1,1,1]])

#morphological operation
temp1 = cv2.erode(tt1, ver1, iterations=2)
verticle_lines_img1 = cv2.dilate(temp1, ver1, iterations=1)

temp12 = cv2.erode(tt1, hor1, iterations=1)
hor_lines_img2 = cv2.dilate(temp12, hor1, iterations=1)

# doing or operation for detecting only text part and removing rest all
hor_ver = cv2.add(hor_lines_img2,verticle_lines_img1)
dim1 = (hor_ver.shape[1],hor_ver.shape[0])
dim = (hor_ver.shape[1]*2,hor_ver.shape[0]*2)

# resizing image to its double size to increase the text size
resized = cv2.resize(hor_ver, dim, interpolation = cv2.INTER_AREA)

#bitwise not operation for fliping the pixel values so as to apply morphological operation such as dilation and erode
want = cv2.bitwise_not(resized)

if(want.shape[0]<1000):
    kernel1 = np.array([[1,1,1]])
    kernel2 = np.array([[1,1],
                        [1,1]])
    kernel3 = np.array([[1,0,1],[0,1,0],
                       [1,0,1]])
else:
    kernel1 = np.array([[1,1,1,1,1,1]])
    kernel2 = np.array([[1,1,1,1,1],
                        [1,1,1,1,1],
                        [1,1,1,1,1],
                        [1,1,1,1,1]])

tt1 = cv2.dilate(want,kernel1,iterations=2)

# getting image back to its original size
resized1 = cv2.resize(tt1, dim1, interpolation = cv2.INTER_AREA)

# Find contours for image, which will detect all the boxes
contours1, hierarchy1 = cv2.findContours(resized1, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

#function to sort contours by its x-axis (top to bottom)
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)


#sorting contours by calling fuction
(cnts, boundingBoxes) = sort_contours(contours1, method="top-to-bottom")

#storing value of all bouding box height
heightlist=[]
for i in range(len(boundingBoxes)):
    heightlist.append(boundingBoxes[i][3])

#sorting height values
heightlist.sort()

sportion = int(.5*len(heightlist))
eportion = int(0.05*len(heightlist))

#taking 50% to 95% values of heights and calculate their mean 
#this will neglect small bounding box which are basically noise 
try:
    medianheight = statistics.mean(heightlist[-sportion:-eportion])
except:
    medianheight = statistics.mean(heightlist[-sportion:-2])

#keeping bounding box which are having height more then 70% of the mean height and deleting all those value where 
# ratio of width to height is less then 0.9
box =[]
imag = iii.copy()
for i in range(len(cnts)):    
    cnt = cnts[i]
    x,y,w,h = cv2.boundingRect(cnt)
    if(h>=.7*medianheight and w/h > 0.9):
        image = cv2.rectangle(imag,(x+4,y-2),(x+w-5,y+h),(0,255,0),1)
        box.append([x,y,w,h])
    # to show image

###Now we have badly detected boxes image as shown

推荐答案

你在正确的轨道上.这是您的方法的延续,稍作修改.这个想法是:

You're on the right track. Here's a continuation of your approach with slight modifications. The idea is:

  1. 获取二值图像.加载图像,转灰度,大津阈值.

  1. Obtain binary image. Load image, convert to grayscale, and Otsu's threshold.

删除所有字符文本轮廓.我们创建一个矩形内核并执行打开以仅保留水平/垂直线.这将有效地使文本变成微小的噪声,因此我们找到轮廓并使用轮廓区域进行过滤以去除它们.

Remove all character text contours. We create a rectangular kernel and perform opening to only keep the horizontal/vertical lines. This will effectively make the text into tiny noise so we find contours and filter using contour area to remove them.

修复水平/垂直线并提取每个 ROI. 我们变形接近修复和断线并平滑表格.从这里我们使用带有 top-to-bottom 参数的 imutils.sort_contours() 对框域轮廓进行排序.接下来我们找到轮廓并使用轮廓区域进行过滤,然后提取每个 ROI.

Repair horizontal/vertical lines and extract each ROI. We morph close to fix and broken lines and smooth the table. From here we sort the box field contours using imutils.sort_contours() with the top-to-bottom parameter. Next we find contours and filter using contour area then extract each ROI.

<小时>

这是每个框字段和提取的 ROI 的可视化


Here's a visualization of each box field and the extracted ROI

代码

import cv2
import numpy as np
from imutils import contours

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

# Remove text characters with morph open and contour filtering
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
cnts = cv2.findContours(opening, 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 < 500:
        cv2.drawContours(opening, [c], -1, (0,0,0), -1)

# Repair table lines, sort contours, and extract ROI
close = 255 - cv2.morphologyEx(opening, cv2.MORPH_CLOSE, kernel, iterations=1)
cnts = cv2.findContours(close, 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:
    area = cv2.contourArea(c)
    if area < 25000:
        x,y,w,h = cv2.boundingRect(c)
        cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), -1)
        ROI = original[y:y+h, x:x+w]

        # Visualization
        cv2.imshow('image', image)
        cv2.imshow('ROI', ROI)
        cv2.waitKey(20)

cv2.imshow('opening', opening)
cv2.imshow('close', close)
cv2.imshow('image', image)
cv2.waitKey()

这篇关于从表格图像中提取单个字段以使用 OCR 进行 Excel的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持跟版网!

本站部分内容来源互联网,如果有图片或者内容侵犯您的权益请联系我们删除!

相关文档推荐

Reading *.mhd/*.raw format in python(在 python 中读取 *.mhd/*.raw 格式)
Count number of cells in the image(计算图像中的单元格数)
How to detect paragraphs in a text document image for a non-consistent text structure in Python OpenCV(如何在 Python OpenCV 中检测文本文档图像中的段落是否存在不一致的文本结构)
How to get the coordinates of the bounding box in YOLO object detection?(YOLO物体检测中如何获取边界框的坐标?)
Divide an image into 5x5 blocks in python and compute histogram for each block(在 python 中将图像划分为 5x5 块并计算每个块的直方图)
Extract cow number from image(从图像中提取奶牛编号)