字符识别

标签：字符识别 img int cv2 yimg pytesseract tesseract

import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd=r'E:\tesseract\tesseract.exe'
#字符识别（英文，数字）
# img = cv2.imread('img_1.png')
# img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
# yimg,ximg,_ = img.shape #(y,x)
# # print(pytesseract.image_to_string(img)) #内容
# # print(pytesseract.image_to_boxes(img)) #字符位置
# boxes = pytesseract.image_to_boxes(img)
# for i in boxes.splitlines():
#     i = i.split(' ')
#     print(i)
#     x,y,w,h = int(i[1]),int(i[2]),int(i[3]),int(i[4])
#     cv2.rectangle(img,(x,yimg-y),(w,yimg-h),(0,0,255),1)
#     cv2.putText(img,i[0],(x,yimg-y),cv2.FONT_HERSHEY_COMPLEX,1,(0,0,255),2)
# cv2.imshow('result',img)
# cv2.waitKey(0)

#字符识别（单词）
# pytesseract.pytesseract.tesseract_cmd=r'E:\tesseract\tesseract.exe'
# img = cv2.imread('img_1.png')
# img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
# yimg,ximg,_ = img.shape #(y,x)
# boexs = pytesseract.image_to_data(img)
# print(boexs)
#第一种方法
# for x,i in enumerate(boexs.splitlines()):
#     if x != 0:
#         i = i.split()
#         print(i)
#第二种方法
# for i in boexs.splitlines()[1::]:
#     i = i.split()
#     print(i)
#     if len(i) == 12:
#         x,y,w,h = int(i[6]),int(i[7]),int(i[8]),int(i[9])
#         cv2.rectangle(img,(x,y),(x+w,y+h),(0,0,255),1)
#         cv2.putText(img,i[11],(x,y),cv2.FONT_HERSHEY_COMPLEX,1,(0,0,255),2)
# cv2.imshow('result',img)
# cv2.waitKey(0)

#字符识别（数字）
# pytesseract.pytesseract.tesseract_cmd=r'E:\tesseract\tesseract.exe'
# img = cv2.imread('img_1.png')
# img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
# yimg,ximg,_ = img.shape #(y,x)
# cong = r'--oem 3 --psm 6 outputbase digits'
# boxes = pytesseract.image_to_boxes(img,config=cong)
# for i in boxes.splitlines():
#     i = i.split(' ')
#     x,y,w,h = int(i[1]),int(i[2]),int(i[3]),int(i[4])
#     cv2.rectangle(img,(x,yimg-y),(w,yimg-h),(0,0,255),1)
#     cv2.putText(img,i[0],(x,yimg-y),cv2.FONT_HERSHEY_COMPLEX,1,(0,0,255),2)
# cv2.imshow('result',img)
# cv2.waitKey(0)

#中文识别
from PIL import Image
img = Image.open('../img_5.png')
text = pytesseract.image_to_string(img,lang='chi_sim')#config='psm - 6'
print(text)

标签：字符识别,img,int,cv2,yimg,pytesseract,tesseract
From： https://www.cnblogs.com/lld76/p/15995190.html