基于PaddleOCR2.7.0发布WebRest服务测试案例-Toy模板网

这篇具有很好参考价值的文章主要介绍了基于PaddleOCR2.7.0发布WebRest服务测试案例。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

基于PaddleOCR2.7.0发布WebRest服务测试案例

#WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
#警告：这是一个开发服务器。不要在生产部署中使用它。请改用生产WSGI服务器。

输出结果：

'''
输出结果
[
    "中华人民共和国,0.9899783730506897",
    "居民身份证,0.9980843663215637",
    "祥证,0.8810203075408936",
    "正,0.9998733997344971",
    "签发机关北京市公安商西城分局,0.9768146872520447",
    "有效期限2004.10.27-2024.10.26,0.9777843952178955",
    "姓名金阳,0.9970041513442993",
    "反,0.8982676267623901",
    "性别女,0.9921286702156067",
    "民族汉,0.7694575190544128",
    "出生1978年10月27日,0.9945864081382751",
    "住址北京市西城区复兴门外大,0.9793714284896851",
    "街999号院11号楼3单元,0.997355043888092",
    "样证502室,0.954838752746582",
    "公民身份号码,0.999056339263916",
    "110102197810272321,0.9936114549636841",
    "头杀@刘海波,0.8078877925872803"
]
'''

postman请求格式：
基于PaddleOCR2.7.0发布WebRest服务测试案例,人工智能,开发语言 Python,笔记

访问地址：http://127.0.0.1:5000/ocr    post模式 参数image_path  
postman 请求格式
Json格式和 image_path=
''' 
{
    "image_path" : "E:/project/python/OCR/data/sfz.jpg"
}
'''

安装paddleocr2.7.0

 激活环境
conda activate  d:\programdata\conda\cwgis 
conda deactivate

采用pip模式查询包的版本列表情况
pip index versions  paddleocr

pip install paddleocr==2.7.0

#兼容性再安装
pip install opencv-python==4.4.0.46
pip install click==8.1.3 
conda install pillow==9.0.1

PaddleOCR版本列表情况

C:\Users\hsgpc>pip index versions  paddleocr
WARNING: pip index is currently an experimental command. It may be removed/changed in a future release without prior warning.
paddleocr (2.7.0.2)
Available versions: 2.7.0.2, 2.7.0.1, 2.7.0.0, 2.6.1.3, 2.6.1.2, 2.6.1.1, 2.6.1.0, 2.6.0.3, 2.6.0.2, 2.6.0.1, 2.6, 2.5.0.3, 2.5.0.2, 2.5, 2.4.0.4, 2.4.0.3, 2.4.0.2, 2.4.0.1, 2.4, 2.3.0.2, 2.3.0.1, 2.3, 2.2.0.2, 2.2.0.1, 2.2, 2.0.6, 2.0.5, 2.0.4, 2.0.3, 2.0.2, 2.0.1, 1.1.1, 1.0.1, 1.0.0, 0.0.3.1, 0.0.3, 0.0.2, 0.0.1.1

C:\Users\hsgpc>

测试的发布服务的代码：

from flask import Flask, request, jsonify
from paddleocr  import PaddleOCR

#报错：ImportError: cannot import name 'ParameterSource' from 'click.core'
#pip index versions click   #查看版本号列表
#随机选择一个版本8.0.0版本，安装时提示flask 2.3.2 requires click>=8.1.3,
#故再次选择安装8.1.3版本 OK
#pip install click==8.1.3

# need to run only once to download and load model into memory
p = PaddleOCR(use_angle_cls=True, lang="ch")  

print(__name__)     #__main__
app = Flask(__name__)

#定义 get 方法 /v
@app.route('/v', methods=['get'])
def v():
    return "1.0.0"

#定义 post  方法  /ocr
@app.route('/ocr', methods=['POST'])
def ocr():
    data = request.get_json()
    image_path = data['image_path']  # 从请求中获取图像路径
    print('image_path=',image_path)
    #ocr_result = PaddleOCR.ocr(image_path, use_gpu=False)  # 调用PaddleOCR模型进行图像识别
    
    ocr_result = p.ocr(image_path, cls=True)
    h_result=[]
    index=1
    for line in ocr_result:   
       for detection in line:
           t=detection[1][0]+","+str(detection[1][1])
           h_result.append(t)
           index+=1
    return jsonify(h_result)  # 将识别结果以JSON格式返回给客户端

if __name__ == '__main__':
    app.run()

#http://127.0.0.1:5000/v     #OK