from PIL import Image
from pytesseract import *
from fnmatch import fnmatch
from queue import Queue
import matplotlib.pyplot as plt
import cv2
import time
import os
def clear_border(img,img_name):
 '''去除邊框
 '''
 filename = './out_img/' + img_name.split('.')[0] + '-clearBorder.jpg'
 h, w = img.shape[:2]
 for y in range(0, w):
 for x in range(0, h):
 # if y ==0 or y == w -1 or y == w - 2:
 if y < 4 or y > w -4:
 img[x, y] = 255
 # if x == 0 or x == h - 1 or x == h - 2:
 if x < 4 or x > h - 4:
 img[x, y] = 255
 cv2.imwrite(filename,img)
 return img
def interference_line(img, img_name):
 '''
 干擾線降噪
 '''
 filename = './out_img/' + img_name.split('.')[0] + '-interferenceline.jpg'
 h, w = img.shape[:2]
 # ！！！opencv矩陣點是反的
 # img[1,2] 1:圖片的高度，2：圖片的寬度
 for y in range(1, w - 1):
 for x in range(1, h - 1):
 count = 0
 if img[x, y - 1] > 245:
 count = count + 1
 if img[x, y + 1] > 245:
 count = count + 1
 if img[x - 1, y] > 245:
 count = count + 1
 if img[x + 1, y] > 245:
 count = count + 1
 if count > 2:
 img[x, y] = 255
 cv2.imwrite(filename,img)
 return img
def interference_point(img,img_name, x = 0, y = 0):
 """點降噪
 9鄰域框,以當前點為中心的田字框,黑點個數
 :param x:
 :param y:
 :return:
 """
 filename = './out_img/' + img_name.split('.')[0] + '-interferencePoint.jpg'
 # todo 判斷圖片的長寬度下限
 cur_pixel = img[x,y]# 當前像素點的值
 height,width = img.shape[:2]
 for y in range(0, width - 1):
 for x in range(0, height - 1):
 if y == 0: # 第一行
 if x == 0: # 左上頂點,4鄰域
 # 中心點旁邊3個點
 sum = int(cur_pixel) 
 + int(img[x, y + 1]) 
 + int(img[x + 1, y]) 
 + int(img[x + 1, y + 1])
 if sum <= 2 * 245:
 img[x, y] = 0
 elif x == height - 1: # 右上頂點
 sum = int(cur_pixel) 
 + int(img[x, y + 1]) 
 + int(img[x - 1, y]) 
 + int(img[x - 1, y + 1])
 if sum <= 2 * 245:
 img[x, y] = 0
 else: # 最上非頂點,6鄰域
 sum = int(img[x - 1, y]) 
 + int(img[x - 1, y + 1]) 
 + int(cur_pixel) 
 + int(img[x, y + 1]) 
 + int(img[x + 1, y]) 
 + int(img[x + 1, y + 1])
 if sum <= 3 * 245:
 img[x, y] = 0
 elif y == width - 1: # 最下面一行
 if x == 0: # 左下頂點
 # 中心點旁邊3個點
 sum = int(cur_pixel) 
 + int(img[x + 1, y]) 
 + int(img[x + 1, y - 1]) 
 + int(img[x, y - 1])
 if sum <= 2 * 245:
 img[x, y] = 0
 elif x == height - 1: # 右下頂點
 sum = int(cur_pixel) 
 + int(img[x, y - 1]) 
 + int(img[x - 1, y]) 
 + int(img[x - 1, y - 1])
 if sum <= 2 * 245:
 img[x, y] = 0
 else: # 最下非頂點,6鄰域
 sum = int(cur_pixel) 
 + int(img[x - 1, y]) 
 + int(img[x + 1, y]) 
 + int(img[x, y - 1]) 
 + int(img[x - 1, y - 1]) 
 + int(img[x + 1, y - 1])
 if sum <= 3 * 245:
 img[x, y] = 0
 else: # y不在邊界
 if x == 0: # 左邊非頂點
 sum = int(img[x, y - 1]) 
 + int(cur_pixel) 
 + int(img[x, y + 1]) 
 + int(img[x + 1, y - 1]) 
 + int(img[x + 1, y]) 
 + int(img[x + 1, y + 1])
 if sum <= 3 * 245:
 img[x, y] = 0
 elif x == height - 1: # 右邊非頂點
 sum = int(img[x, y - 1]) 
 + int(cur_pixel) 
 + int(img[x, y + 1]) 
 + int(img[x - 1, y - 1]) 
 + int(img[x - 1, y]) 
 + int(img[x - 1, y + 1])
 if sum <= 3 * 245:
 img[x, y] = 0
 else: # 具備9領域條件的
 sum = int(img[x - 1, y - 1]) 
 + int(img[x - 1, y]) 
 + int(img[x - 1, y + 1]) 
 + int(img[x, y - 1]) 
 + int(cur_pixel) 
 + int(img[x, y + 1]) 
 + int(img[x + 1, y - 1]) 
 + int(img[x + 1, y]) 
 + int(img[x + 1, y + 1])
 if sum <= 4 * 245:
 img[x, y] = 0
 cv2.imwrite(filename,img)
 return img
def _get_dynamic_binary_image(filedir, img_name):
 '''
 自適應閥值二值化
 '''
 filename = './out_img/' + img_name.split('.')[0] + '-binary.jpg'
 img_name = filedir + '/' + img_name
 print('.....' + img_name)
 im = cv2.imread(img_name)
 im = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
 th1 = cv2.adaptiveThreshold(im, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 21, 1)
 cv2.imwrite(filename,th1)
 return th1
def _get_static_binary_image(img, threshold = 140):
 '''
 手動二值化
 '''
 img = Image.open(img)
 img = img.convert('L')
 pixdata = img.load()
 w, h = img.size
 for y in range(h):
 for x in range(w):
 if pixdata[x, y] < threshold:
 pixdata[x, y] = 0
 else:
 pixdata[x, y] = 255
 return img
def cfs(im,x_fd,y_fd):
 '''用隊列和集合記錄遍歷過的像素坐標代替單純遞歸以解決cfs訪問過深問題
 '''
 # print('**********')
 xaxis=[]
 yaxis=[]
 visited =set()
 q = Queue()
 q.put((x_fd, y_fd))
 visited.add((x_fd, y_fd))
 offsets=[(1, 0), (0, 1), (-1, 0), (0, -1)]#四鄰域
 while not q.empty():
 x,y=q.get()
 for xoffset,yoffset in offsets:
 x_neighbor,y_neighbor = x+xoffset,y+yoffset
 if (x_neighbor,y_neighbor) in (visited):
 continue # 已經訪問過了
 visited.add((x_neighbor, y_neighbor))
 try:
 if im[x_neighbor, y_neighbor] == 0:
 xaxis.append(x_neighbor)
 yaxis.append(y_neighbor)
 q.put((x_neighbor,y_neighbor))
 except IndexError:
 pass
 # print(xaxis)
 if (len(xaxis) == 0 | len(yaxis) == 0):
 xmax = x_fd + 1
 xmin = x_fd
 ymax = y_fd + 1
 ymin = y_fd
 else:
 xmax = max(xaxis)
 xmin = min(xaxis)
 ymax = max(yaxis)
 ymin = min(yaxis)
 #ymin,ymax=sort(yaxis)
 return ymax,ymin,xmax,xmin
def detectFgPix(im,xmax):
 '''搜索區塊起點
 '''
 h,w = im.shape[:2]
 for y_fd in range(xmax+1,w):
 for x_fd in range(h):
 if im[x_fd,y_fd] == 0:
 return x_fd,y_fd
def CFS(im):
 '''切割字符位置
 '''
 zoneL=[]#各區塊長度L列表
 zoneWB=[]#各區塊的X軸[起始，終點]列表
 zoneHB=[]#各區塊的Y軸[起始，終點]列表
 xmax=0#上一區塊結束黑點橫坐標,這里是初始化
 for i in range(10):
 try:
 x_fd,y_fd = detectFgPix(im,xmax)
 # print(y_fd,x_fd)
 xmax,xmin,ymax,ymin=cfs(im,x_fd,y_fd)
 L = xmax - xmin
 H = ymax - ymin
 zoneL.append(L)
 zoneWB.append([xmin,xmax])
 zoneHB.append([ymin,ymax])
 except TypeError:
 return zoneL,zoneWB,zoneHB
 return zoneL,zoneWB,zoneHB
def cutting_img(im,im_position,img,xoffset = 1,yoffset = 1):
 filename = './out_img/' + img.split('.')[0]
 # 識別出的字符個數
 im_number = len(im_position[1])
 # 切割字符
 for i in range(im_number):
 im_start_X = im_position[1][i][0] - xoffset
 im_end_X = im_position[1][i][1] + xoffset
 im_start_Y = im_position[2][i][0] - yoffset
 im_end_Y = im_position[2][i][1] + yoffset
 cropped = im[im_start_Y:im_end_Y, im_start_X:im_end_X]
 cv2.imwrite(filename + '-cutting-' + str(i) + '.jpg',cropped)
def main():
 filedir = './easy_img'
 for file in os.listdir(filedir):
 if fnmatch(file, '*.jpeg'):
 img_name = file
 # 自適應閾值二值化
 im = _get_dynamic_binary_image(filedir, img_name)
 # 去除邊框
 im = clear_border(im,img_name)
 # 對圖片進行干擾線降噪
 im = interference_line(im,img_name)
 # 對圖片進行點降噪
 im = interference_point(im,img_name)
 # 切割的位置
 im_position = CFS(im)
 maxL = max(im_position[0])
 minL = min(im_position[0])
 # 如果有粘連字符，如果一個字符的長度過長就認為是粘連字符，并從中間進行切割
 if(maxL > minL + minL * 0.7):
 maxL_index = im_position[0].index(maxL)
 minL_index = im_position[0].index(minL)
 # 設置字符的寬度
 im_position[0][maxL_index] = maxL // 2
 im_position[0].insert(maxL_index + 1, maxL // 2)
 # 設置字符X軸[起始，終點]位置
 im_position[1][maxL_index][1] = im_position[1][maxL_index][0] + maxL // 2
 im_position[1].insert(maxL_index + 1, [im_position[1][maxL_index][1] + 1, im_position[1][maxL_index][1] + 1 + maxL // 2])
 # 設置字符的Y軸[起始，終點]位置
 im_position[2].insert(maxL_index + 1, im_position[2][maxL_index])
 # 切割字符，要想切得好就得配置參數，通常 1 or 2 就可以
 cutting_img(im,im_position,img_name,1,1)
 # 識別驗證碼
 cutting_img_num = 0
 for file in os.listdir('./out_img'):
 str_img = ''
 if fnmatch(file, '%s-cutting-*.jpg' % img_name.split('.')[0]):
 cutting_img_num += 1
 for i in range(cutting_img_num):
 try:
 file = './out_img/%s-cutting-%s.jpg' % (img_name.split('.')[0], i)
 # 識別驗證碼
 str_img = str_img + image_to_string(Image.open(file),lang = 'eng', config='-psm 10') #單個字符是10，一行文本是7
 except Exception as err:
 pass
 print('切圖：%s' % cutting_img_num)
 print('識別為：%s' % str_img)
if __name__ == '__main__':
 main()