今天咋们继续利用pillow和pytesseract来实现验证码的识别
一、环境配置
-
需要 pillow 和 pytesseract 这两个库,pip install 安装就好了。
- pip 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。
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
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
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
- 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 设置阈值 自适应阈值的话 黄色的4会提取不出来
- ret, binary = cv.threshold(gray, 185, 255, cv.THRESH_BINARY_INV)
- print(f'二值化设置的阈值:{ret}')
- cv.imshow('binary', binary)
- # 逻辑运算 让背景为白色 字体为黑 便于识别
- cv.bitwise_not(binary, binary)
- cv.imshow('bg_image', binary)
- # 识别
- test_message = Image.fromarray(binary)
- text = pytesseract.image_to_string(test_message)
- print(f'识别结果:{text}')
-
-
- src = cv.imread(r'./test/045.jpg')
- cv.imshow('input image', src)
- recognize_text(src)
- cv.waitKey(0)
- cv.destroyAllWindows()
-
运行效果如下:
- 二值化设置的阈值:185.0
- 识别结果:7364
-
- Process finished with exit code 0
结语
以上就是这篇文章的全部内容了,希望本文的内容对大家的学习或者工作具有一定的参考学习价值,谢谢大家对小编的支持。