import cv2 import pytesseract

安装tesseract-OCR，并配置路径

pytesseract.pytesseract.tesseract_cmd = r'D:\tesseract-ocr\tesseract.exe'

读取图像

img = cv2.imread('C:/Users/jian.gao/Desktop/8eaec849-326d-4e1e-a61a-e9f6a73c3ea2.jpg')

转换为灰度图像

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

二值化处理

thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

腐蚀操作，去除噪声

kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3)) erode = cv2.erode(thresh, kernel, iterations=1)

进行开运算，去除噪声和粘连部分

opening_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)) opening = cv2.morphologyEx(erode, cv2.MORPH_OPEN, opening_kernel)

识别图像中的文字

text = pytesseract.image_to_string(opening, lang='chi_sim', config='--psm 6')

print(text)

显示图像

cv2.imshow('image', img)

cv2.imshow('gray', gray)

cv2.imshow('thresh', thresh)

cv2.imshow('erode', erode)

cv2.imshow('opening', opening)

cv2.waitKey(0)

cv2.destroyAllWindows()