快捷導(dǎo)航

python驗(yàn)證碼識別教程之利用滴水算法分割圖片

更新時(shí)間：2018年06月05日 08:38:14 作者：Hi!Roy!

這篇文章主要給大家介紹了關(guān)于python驗(yàn)證碼識別教程之利用滴水算法分割圖片的相關(guān)資料，文章中通過示例代碼介紹的非常詳細(xì)，對大家的學(xué)習(xí)或者具有一定的參考學(xué)習(xí)價(jià)值，需要的朋友們下面隨著小編來一起學(xué)習(xí)學(xué)習(xí)吧

滴水算法概述

滴水算法是一種用于分割手寫粘連字符的算法，與以往的直線式地分割不同，它模擬水滴的滾動，通過水滴的滾動路徑來分割字符，可以解決直線切割造成的過分分割問題。

引言

之前提過對于有粘連的字符可以使用滴水算法來解決分割，但智商捉急的我實(shí)在是領(lǐng)悟不了這個(gè)算法的精髓，幸好有小伙伴已經(jīng)實(shí)現(xiàn)相關(guān)代碼。

我對上面的代碼進(jìn)行了一些小修改，同時(shí)升級為python3的代碼。

還是以這張圖片為例：

在以前的我們已經(jīng)知道這種簡單的粘連可以通過控制閾值來實(shí)現(xiàn)分割，這里我們使用滴水算法。

首先使用之前文章中介紹的垂直投影或者連通域先進(jìn)行一次切割處理，得到結(jié)果如下：

針對于最后粘連情況來使用滴水算法處理：

from itertools import groupby

def binarizing(img,threshold):
 """傳入image對象進(jìn)行灰度、二值處理"""
 img = img.convert("L") # 轉(zhuǎn)灰度
 pixdata = img.load()
 w, h = img.size
 # 遍歷所有像素，大于閾值的為黑色
 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 vertical(img):
 """傳入二值化后的圖片進(jìn)行垂直投影"""
 pixdata = img.load()
 w,h = img.size
 result = []
 for x in range(w):
  black = 0
  for y in range(h):
   if pixdata[x,y] == 0:
    black += 1
  result.append(black)
 return result

def get_start_x(hist_width):
 """根據(jù)圖片垂直投影的結(jié)果來確定起點(diǎn)
  hist_width中間值 前后取4個(gè)值 再這范圍內(nèi)取最小值
 """
 mid = len(hist_width) // 2 # 注意py3 除法和py2不同
 temp = hist_width[mid-4:mid+5]
 return mid - 4 + temp.index(min(temp))

def get_nearby_pix_value(img_pix,x,y,j):
 """獲取臨近5個(gè)點(diǎn)像素?cái)?shù)據(jù)"""
 if j == 1:
  return 0 if img_pix[x-1,y+1] == 0 else 1
 elif j ==2:
  return 0 if img_pix[x,y+1] == 0 else 1
 elif j ==3:
  return 0 if img_pix[x+1,y+1] == 0 else 1
 elif j ==4:
  return 0 if img_pix[x+1,y] == 0 else 1
 elif j ==5:
  return 0 if img_pix[x-1,y] == 0 else 1
 else:
  raise Exception("get_nearby_pix_value error")


def get_end_route(img,start_x,height):
 """獲取滴水路徑"""
 left_limit = 0
 right_limit = img.size[0] - 1
 end_route = []
 cur_p = (start_x,0)
 last_p = cur_p
 end_route.append(cur_p)

 while cur_p[1] < (height-1):
  sum_n = 0
  max_w = 0
  next_x = cur_p[0]
  next_y = cur_p[1]
  pix_img = img.load()
  for i in range(1,6):
   cur_w = get_nearby_pix_value(pix_img,cur_p[0],cur_p[1],i) * (6-i)
   sum_n += cur_w
   if max_w < cur_w:
    max_w = cur_w
  if sum_n == 0:
   # 如果全黑則看慣性
   max_w = 4
  if sum_n == 15:
   max_w = 6

  if max_w == 1:
   next_x = cur_p[0] - 1
   next_y = cur_p[1]
  elif max_w == 2:
   next_x = cur_p[0] + 1
   next_y = cur_p[1]
  elif max_w == 3:
   next_x = cur_p[0] + 1
   next_y = cur_p[1] + 1
  elif max_w == 5:
   next_x = cur_p[0] - 1
   next_y = cur_p[1] + 1
  elif max_w == 6:
   next_x = cur_p[0]
   next_y = cur_p[1] + 1
  elif max_w == 4:
   if next_x > cur_p[0]:
    # 向右
    next_x = cur_p[0] + 1
    next_y = cur_p[1] + 1
   if next_x < cur_p[0]:
    next_x = cur_p[0]
    next_y = cur_p[1] + 1
   if sum_n == 0:
    next_x = cur_p[0]
    next_y = cur_p[1] + 1
  else:
   raise Exception("get end route error")

  if last_p[0] == next_x and last_p[1] == next_y:
   if next_x < cur_p[0]:
    max_w = 5
    next_x = cur_p[0] + 1
    next_y = cur_p[1] + 1
   else:
    max_w = 3
    next_x = cur_p[0] - 1
    next_y = cur_p[1] + 1
  last_p = cur_p

  if next_x > right_limit:
   next_x = right_limit
   next_y = cur_p[1] + 1
  if next_x < left_limit:
   next_x = left_limit
   next_y = cur_p[1] + 1
  cur_p = (next_x,next_y)
  end_route.append(cur_p)
 return end_route

def get_split_seq(projection_x):
 split_seq = []
 start_x = 0
 length = 0
 for pos_x, val in enumerate(projection_x):
  if val == 0 and length == 0:
   continue
  elif val == 0 and length != 0:
   split_seq.append([start_x, length])
   length = 0
  elif val == 1:
   if length == 0:
    start_x = pos_x
   length += 1
  else:
   raise Exception('generating split sequence occurs error')
 # 循環(huán)結(jié)束時(shí)如果length不為0，說明還有一部分需要append
 if length != 0:
  split_seq.append([start_x, length])
 return split_seq


def do_split(source_image, starts, filter_ends):
 """
 具體實(shí)行切割
 : param starts: 每一行的起始點(diǎn) tuple of list
 : param ends: 每一行的終止點(diǎn)
 """
 left = starts[0][0]
 top = starts[0][1]
 right = filter_ends[0][0]
 bottom = filter_ends[0][1]
 pixdata = source_image.load()
 for i in range(len(starts)):
  left = min(starts[i][0], left)
  top = min(starts[i][1], top)
  right = max(filter_ends[i][0], right)
  bottom = max(filter_ends[i][1], bottom)
 width = right - left + 1
 height = bottom - top + 1
 image = Image.new('RGB', (width, height), (255,255,255))
 for i in range(height):
  start = starts[i]
  end = filter_ends[i]
  for x in range(start[0], end[0]+1):
   if pixdata[x,start[1]] == 0:
    image.putpixel((x - left, start[1] - top), (0,0,0))
 return image

def drop_fall(img):
 """滴水分割"""
 width,height = img.size
 # 1 二值化
 b_img = binarizing(img,200)
 # 2 垂直投影
 hist_width = vertical(b_img)
 # 3 獲取起點(diǎn)
 start_x = get_start_x(hist_width)

 # 4 開始滴水算法
 start_route = []
 for y in range(height):
  start_route.append((0,y))

 end_route = get_end_route(img,start_x,height)
 filter_end_route = [max(list(k)) for _,k in groupby(end_route,lambda x:x[1])] # 注意這里groupby
 img1 = do_split(img,start_route,filter_end_route)
 img1.save('cuts-d-1.png')

 start_route = list(map(lambda x : (x[0]+1,x[1]),filter_end_route)) # python3中map不返回list需要自己轉(zhuǎn)換
 end_route = []
 for y in range(height):
  end_route.append((width-1,y))
 img2 = do_split(img,start_route,end_route)
 img2.save('cuts-d-2.png')

if __name__ == '__main__':
 p = Image.open("cuts-2.png")
 drop_fall(p)

執(zhí)行后會得到切分后的2個(gè)照片：