Python下3种文字识别工具的源码和效果比较

最新推荐文章于 2024-09-27 10:11:28 发布

eybk

最新推荐文章于 2024-09-27 10:11:28 发布

阅读量994

点赞数 11

文章标签： python 开发语言

本文链接：https://blog.csdn.net/2401_82434226/article/details/139676388

版权

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 = image_to_base64(img)
   
    response = requests.post(url, data = data, headers=headers)
    
    if response:
        result = json.loads(str(response.content, 'utf-8'))
        dic = result['PaddleOCR']
        i = 0
        while i < len(dic):
            tt = dic[i]['ttxt']
            print(tt)
            i = i + 1

小学常用3500字顺口溜 pytesseract

中华历史岁月五千文武成康治乱存亡渊源流长古往今来雪雨风霜

王侯将相公卿大夫敢于担当塞外边疆秦皇汉武汉刘曹魏李唐赵宋

功成名就三番五次征战讨伐改朝换代睁是瞬间辉煌灿烂耳闻目见

记忆忘却惊险刺激孤单寂寞喜怒哀乐悲欢离合休福灾咎胜败输赢

阴晴圆缺福祸旦夕和谐融洽散虑遂遥烦闷愧恼

大小多少远近高低高矮胖瘦长短粗细日月水火山石田士男女老少

先来后到黄名其妙护卫保镖穿衣戴帽众多寡少幼稚孩童活泼可爱

士农工商兵学官警描图绘画飞黄腾达飞鸟走兽游鱼耻虫江河湖海

之乎者也和爷娘姑舅端庄秀丽撑持维系操持把握落花流水刮风下雨

东南西北年月日时钟表铃匀宾客朋友善始令终紧迫缓冲队伍军团

迅速疾快挑担打抬酒圳饭袋熬汤问饭张灯结彩观望视看佛道神仙