Python下3种文字识别工具的源码和效果比较

1.pytesseract

import pytesseract
from PIL import Image

im = Image.open(r'C:/Users/YBK/Pictures/35005.jpg')
string = pytesseract.image_to_string(im,lang='chi_sim')
print(string)

2.paddleocr

from paddleocr import PaddleOCR, draw_ocr

ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
img_path = r'C:/Users/YBK/Pictures/35005.jpg'
result = ocr.ocr(img_path, cls=True)
# for line in result:
#     print(line)
 
# 显示结果
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [detection[0] for line in result for detection in line] # Nested loop added
txts = [detection[1][0] for line in result for detection in line] # Nested loop added
scores = [detection[1][1] for line in result for detection in line] # Nested loop added
# im_show = draw_ocr(image, boxes, txts, scores)
# im_show = Image.fromarray(im_show)
# im_show.save('test.jpg')
for tt in txts:
    print(tt)

3.某个易语言程序的接口

from urllib import request, parse
import requests
import base64
import json
from urllib.request import urlretrieve
import os
import cv2
import base64
import numpy as np
import time
import pandas as pd
 
 
def image_to_base64(image_mat):
    image = cv2.imencode('.jpg', image_mat)[1]
    image_code = str(base64.b64encode(image), 'utf-8')
    return image_code
 
if __name__ == '__main__':
    url = "http://127.0.0.1:19811/ocr_data_2"
    testImgp = r'C:/Users/YBK/Pictures/35005.jpg'
    img = cv2.imread(testImgp)
    headers = {'content-type': "application/json"}
 
    data