【python 图像识别】图像识别从菜鸟走向大神系列1
程序员文章站
2024-03-15 23:30:18
...
一、安装配置(python2.7)
1.pip install pytesseract
2、pip install pyocr
3、pip install pillow
4、安装tesseract-ocr:http://jaist.dl.sourceforge.net/project/tesseract-ocr-alt/tesseract-ocr-setup-3.02.02.exe,安装在C:\Program Files\下
5、找到 pytesseract.py 更改 tesseract_cmd = 'C:/Program Files/Tesseract-OCR/tesseract.exe'
- 1
- 2
- 3
- 4
- 5
- 1
- 2
- 3
- 4
- 5
二、识别英文
三、识别验证码
二、实现源代码
1、识别英文
#-*-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)
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
2、识别验证码
#-*-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')
###########去除干扰线算法
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
# 转化为灰度图
img = image.convert('L')
# 把图片变成二值图像。
img1=binarizing(img,190)
# img2=depoint(img1)
img1.show()
code = pytesseract.image_to_string(img1)
print "识别该验证码是:" + str(code)