import cv2

import pytesseract

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

img = cv2.imread('C:/Users/jian.gao/Desktop/1.jpg')

缩小图片尺寸，去除噪声

img = cv2.resize(img, None, fx=0.5, fy=0.5, interpolation=cv2.INTER_AREA)

将彩色图像转换为灰度图像

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

对图像进行二值化处理

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

对图像进行膨胀操作，填充空洞

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

对图像进行腐蚀操作，去除噪声

erode = cv2.erode(dilate, kernel, iterations=1)

识别图像中的文字

text = pytesseract.image_to_string(erode, lang='chi_sim')

print(text)

显示图片和二值化后的图片

cv2.imshow('image', img) cv2.imshow('erode', erode) cv2.waitKey(0) cv2.destroyAllWindows()