# -*- coding: utf-8 -*-
"""
Created on Tue May 28 19:23:19 2019
將圖片按照表格框線交叉點(diǎn)分割成子圖片（傳入圖片路徑）
@author: hx
"""
 
import cv2
import numpy as np
import pytesseract
 
image = cv2.imread('C:/Users/Administrator/Desktop/7.jpg', 1)
#灰度圖片
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#二值化
binary = cv2.adaptiveThreshold(~gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 35, -5)
#ret,binary = cv2.threshold(~gray, 127, 255, cv2.THRESH_BINARY)
cv2.imshow("二值化圖片：", binary) #展示圖片
cv2.waitKey(0)
 
rows,cols=binary.shape
scale = 40
#識(shí)別橫線
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(cols//scale,1))
eroded = cv2.erode(binary,kernel,iterations = 1)
#cv2.imshow("Eroded Image",eroded)
dilatedcol = cv2.dilate(eroded,kernel,iterations = 1)
cv2.imshow("表格橫線展示：",dilatedcol)
cv2.waitKey(0)
 
#識(shí)別豎線
scale = 20
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(1,rows//scale))
eroded = cv2.erode(binary,kernel,iterations = 1)
dilatedrow = cv2.dilate(eroded,kernel,iterations = 1)
cv2.imshow("表格豎線展示：",dilatedrow)
cv2.waitKey(0)
 
#標(biāo)識(shí)交點(diǎn)
bitwiseAnd = cv2.bitwise_and(dilatedcol,dilatedrow)
cv2.imshow("表格交點(diǎn)展示：",bitwiseAnd)
cv2.waitKey(0)
# cv2.imwrite("my.png",bitwiseAnd) #將二值像素點(diǎn)生成圖片保存
 
#標(biāo)識(shí)表格
merge = cv2.add(dilatedcol,dilatedrow)
cv2.imshow("表格整體展示：",merge)
cv2.waitKey(0)
 
 
#兩張圖片進(jìn)行減法運(yùn)算，去掉表格框線
merge2 = cv2.subtract(binary,merge)
cv2.imshow("圖片去掉表格框線展示：",merge2)
cv2.waitKey(0)
 
#識(shí)別黑白圖中的白色交叉點(diǎn)，將橫縱坐標(biāo)取出
ys,xs = np.where(bitwiseAnd>0)
 
mylisty=[] #縱坐標(biāo)
mylistx=[] #橫坐標(biāo)
 
#通過排序，獲取跳變的x和y的值，說明是交點(diǎn)，否則交點(diǎn)會(huì)有好多像素值值相近，我只取相近值的最后一點(diǎn)
#這個(gè)10的跳變不是固定的，根據(jù)不同的圖片會(huì)有微調(diào)，基本上為單元格表格的高度（y坐標(biāo)跳變）和長(zhǎng)度（x坐標(biāo)跳變）
i = 0
myxs=np.sort(xs)
for i in range(len(myxs)-1):
  if(myxs[i+1]-myxs[i]>10):
    mylistx.append(myxs[i])
  i=i+1
mylistx.append(myxs[i]) #要將最后一個(gè)點(diǎn)加入
 
 
i = 0
myys=np.sort(ys)
#print(np.sort(ys))
for i in range(len(myys)-1):
  if(myys[i+1]-myys[i]>10):
    mylisty.append(myys[i])
  i=i+1
mylisty.append(myys[i]) #要將最后一個(gè)點(diǎn)加入
 
print('mylisty',mylisty)
print('mylistx',mylistx)
 
 
#循環(huán)y坐標(biāo)，x坐標(biāo)分割表格
for i in range(len(mylisty)-1):
  for j in range(len(mylistx)-1):
    #在分割時(shí)，第一個(gè)參數(shù)為y坐標(biāo)，第二個(gè)參數(shù)為x坐標(biāo)
    ROI = image[mylisty[i]+3:mylisty[i+1]-3,mylistx[j]:mylistx[j+1]-3] #減去3的原因是由于我縮小ROI范圍
    cv2.imshow("分割后子圖片展示：",ROI)
    cv2.waitKey(0)
 
    #special_char_list = '`~!@#$%^&*()-_=+[]{}|\\;:‘'，?！丁?？ˇ'
    pytesseract.pytesseract.tesseract_cmd = 'E:/Tesseract-OCR/tesseract.exe'
    text1 = pytesseract.image_to_string(ROI) #讀取文字，此為默認(rèn)英文
    #text2 = ''.join([char for char in text2 if char not in special_char_list])
    print('識(shí)別分割子圖片信息為：'+text1)
    j=j+1
  i=i+1