python基础教程python opencv pytesseract 验证码识别的实现

落日映苍穹つ 2022-12-19 09:31 231阅读 0赞

更多教程请到：菜鸟教程 https://www.piaodoo.com/

**一、环境配置**

需要 pillow 和 pytesseract 这两个库，pip install 安装就好了。

install pillow -i http://pypi.douban.com/simple --trusted-host pypi.douban.com
    pip install pytesseract -i http://pypi.douban.com/simple --trusted-host pypi.douban.com

安装好Tesseract-OCR.exe

pytesseract 库的配置：搜索找到pytesseract.py，打开该.py文件，找到 tesseract\_cmd，改变它的值为刚才安装 tesseract.exe 的路径。

![Image 1][]

**二、验证码识别**

识别验证码，需要先对图像进行预处理，去除会影响识别准确度的线条或噪点，提高识别准确度。

实例1

import cv2 as cv
    import pytesseract
    from PIL import Image

def recognize\_text(image):

# 边缘保留滤波 去噪 #

dst = cv.pyrMeanShiftFiltering(image, sp=10, sr=150)

# 灰度图像 #

gray = cv.cvtColor(dst, cv.COLOR\_BGR2GRAY)

# 二值化 #

ret, binary = cv.threshold(gray, 0, 255, cv.THRESH\_BINARY\_INV | cv.THRESH\_OTSU)

# 形态学操作 腐蚀 膨胀 #

erode = cv.erode(binary, None, iterations=2)  
dilate = cv.dilate(erode, None, iterations=1)  
cv.imshow(‘dilate’, dilate)

# 逻辑运算 让背景为白色 字体为黑 便于识别 #

cv.bitwise\_not(dilate, dilate)  
cv.imshow(‘binary-image’, dilate)

# 识别 #

test\_message = Image.fromarray(dilate)  
text = pytesseract.image\_to\_string(test\_message)  
print(f’识别结果：\{text\}’)

src = cv.imread(r’./test/044.png’)  
cv.imshow(‘input image’, src)  
recognize\_text(src)  
cv.waitKey(0)  
cv.destroyAllWindows()

运行效果如下：

> 识别结果：3n3D
> 
> Process finished with exit code 0  
>

![Image 1][]

实例2

import cv2 as cv
    import pytesseract
    from PIL import Image

def recognize\_text(image):

# 边缘保留滤波 去噪 #

blur =cv.pyrMeanShiftFiltering(image, sp=8, sr=60)  
cv.imshow(‘dst’, blur)

# 灰度图像 #

gray = cv.cvtColor(blur, cv.COLOR\_BGR2GRAY)

# 二值化 #

ret, binary = cv.threshold(gray, 0, 255, cv.THRESH\_BINARY\_INV | cv.THRESH\_OTSU)  
print(f’二值化自适应阈值：\{ret\}’)  
cv.imshow(‘binary’, binary)

# 形态学操作 获取结构元素 开操作 #

kernel = cv.getStructuringElement(cv.MORPH\_RECT, (3, 2))  
bin1 = cv.morphologyEx(binary, cv.MORPH\_OPEN, kernel)  
cv.imshow(‘bin1’, bin1)  
kernel = cv.getStructuringElement(cv.MORPH\_OPEN, (2, 3))  
bin2 = cv.morphologyEx(bin1, cv.MORPH\_OPEN, kernel)  
cv.imshow(‘bin2’, bin2)

# 逻辑运算 让背景为白色 字体为黑 便于识别 #

cv.bitwise\_not(bin2, bin2)  
cv.imshow(‘binary-image’, bin2)

# 识别 #

test\_message = Image.fromarray(bin2)  
text = pytesseract.image\_to\_string(test\_message)  
print(f’识别结果：\{text\}’)

src = cv.imread(r’./test/045.png’)  
cv.imshow(‘input image’, src)  
recognize\_text(src)  
cv.waitKey(0)  
cv.destroyAllWindows()

运行效果如下：

> 二值化自适应阈值：181.0  
> 识别结果：8A62N1
> 
> Process finished with exit code 0  
>

![Image 1][]

实例3

import cv2 as cv
    import pytesseract
    from PIL import Image

def recognize\_text(image):

# 边缘保留滤波 去噪 #