一、安裝配置（python2.7）

1.pip install pytesseract
2、pip install pyocr
3、pip install pillow
4、安裝tesseract-ocr：http://jaist.dl.sourceforge.net/project/tesseract-ocr-alt/tesseract-ocr-setup-3.02.02.exe，安裝在C:\Program Files\下
5、找到 pytesseract.py 更改 tesseract_cmd = 'C:/Program Files/Tesseract-OCR/tesseract.exe'

二、識別英文

三、識別驗證碼

二、實現原始碼
1、識別英文

#-*-coding:utf-8-*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

import time
time1 = time.time()
from PIL import Image
import pytesseract


image = Image.open(r'D:\Program Files\Python27\Lib\site-packages\pytesseract\test.png')
code = pytesseract.image_to_string(image)
print(code)
 

2、識別驗證碼

#-*-coding:utf-8-*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

import time
time1 = time.time()
from PIL import Image
import pytesseract

###########二值化演算法
def binarizing(img,threshold):
    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
image = Image.open(r'E:\taqu\12.png')

###########去除干擾線演算法
def depoint(img):   #input: gray image
    pixdata = img.load()
    w,h = img.size
    for y in range(1,h-1):
        for x in range(1,w-1):
            count = 0
            if pixdata[x,y-1] > 245:
                count = count + 1
            if pixdata[x,y+1] > 245:
                count = count + 1
            if pixdata[x-1,y] > 245:
                count = count + 1
            if pixdata[x+1,y] > 245:
                count = count + 1
            if count > 2:
                pixdata[x,y] = 255
    return img



# 轉化為灰度圖
img = image.convert('L')
# 把圖片變成二值影象。
img1=binarizing(img,190)
# img2=depoint(img1)
img1.show()
code = pytesseract.image_to_string(img1)
print "識別該驗證碼是:" + str(code)