某個招聘網站的驗證碼識別,過程如下
一: 原始驗證碼:
二: 首先對驗證碼進行分析,該驗證碼的數字顏色有變化,這個就是識別這個驗證碼遇到的比較難的問題,解決方法是使用PIL 中的 getpixel 方法進行變色處理,統一把非黑色的畫素點變成黑色
變色後的圖片
三: 通過觀察,發現該驗證碼有折線,需要對圖片進行降噪處理。
降噪後的圖片
四:識別:
這裡只是簡單的使用 pytesseract 模組進行識別
識別結果如下:
總共十一個驗證碼,識別出來了9個,綜合識別率是百分之八十。
總結:驗證碼識別只是簡單呼叫了一下Python的第三方庫,本驗證碼的識別難點如果給帶顏色的數字變色。
下面是程式碼:
二值化變色:
#-*-coding:utf-8-*- from PIL import Image def test(path): img=Image.open(path) w,h=img.size for x in range(w): for y in range(h): r,g,b=img.getpixel((x,y)) if 190<=r<=255 and 170<=g<=255 and 0<=b<=140: img.putpixel((x,y),(0,0,0)) if 0<=r<=90 and 210<=g<=255 and 0<=b<=90: img.putpixel((x,y),(0,0,0)) img=img.convert('L').point([0]*150+[1]*(256-150),'1') return img for i in range(1,13): path = str(i) + '.jpg' im = test(path) path = path.replace('jpg','png') im.save(path)
二:降噪
#-*-coding:utf-8-*- # coding:utf-8 import sys, os from PIL import Image, ImageDraw # 二值陣列 t2val = {} def twoValue(image, G): for y in xrange(0, image.size[1]): for x in xrange(0, image.size[0]): g = image.getpixel((x, y)) if g > G: t2val[(x, y)] = 1 else: t2val[(x, y)] = 0 # 根據一個點A的RGB值,與周圍的8個點的RBG值比較,設定一個值N(0 <N <8),當A的RGB值與周圍8個點的RGB相等數小於N時,此點為噪點 # G: Integer 影象二值化閥值 # N: Integer 降噪率 0 <N <8 # Z: Integer 降噪次數 # 輸出 # 0:降噪成功 # 1:降噪失敗 def clearNoise(image, N, Z): for i in xrange(0, Z): t2val[(0, 0)] = 1 t2val[(image.size[0] - 1, image.size[1] - 1)] = 1 for x in xrange(1, image.size[0] - 1): for y in xrange(1, image.size[1] - 1): nearDots = 0 L = t2val[(x, y)] if L == t2val[(x - 1, y - 1)]: nearDots += 1 if L == t2val[(x - 1, y)]: nearDots += 1 if L == t2val[(x - 1, y + 1)]: nearDots += 1 if L == t2val[(x, y - 1)]: nearDots += 1 if L == t2val[(x, y + 1)]: nearDots += 1 if L == t2val[(x + 1, y - 1)]: nearDots += 1 if L == t2val[(x + 1, y)]: nearDots += 1 if L == t2val[(x + 1, y + 1)]: nearDots += 1 if nearDots < N: t2val[(x, y)] = 1 def saveImage(filename, size): image = Image.new("1", size) draw = ImageDraw.Draw(image) for x in xrange(0, size[0]): for y in xrange(0, size[1]): draw.point((x, y), t2val[(x, y)]) image.save(filename) for i in range(1,12): path = str(i) + ".png" image = Image.open(path).convert("L") twoValue(image, 100) clearNoise(image, 3, 2) path1 = str(i) + ".jpeg" saveImage(path1, image.size)
三:識別
#-*-coding:utf-8-*- from PIL import Image import pytesseract def recognize_captcha(img_path): im = Image.open(img_path) # threshold = 140 # table = [] # for i in range(256): # if i < threshold: # table.append(0) # else: # table.append(1) # # out = im.point(table, '1') num = pytesseract.image_to_string(im) return num if __name__ == '__main__': for i in range(1, 12): img_path = str(i) + ".jpeg" res = recognize_captcha(img_path) strs = res.split("\n") if len(strs) >=1: print (strs[0])